© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9131
    Prev
    Next
    INDEX
    Explanations

    bytes representation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is looking for programming‐related tokens—especially code identifiers, member or function names (e.g. object properties and API calls) in source snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code-related terms, particularly object properties and method calls accessed via dot notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    references to programming code elements, especially object/class member accesses and API method or property names within code snippets.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     three
    0.55
     four
    0.55
    三种
    0.50
    ण्या
    0.50
     تھیں
    0.50
     two
    0.49
     Пари
    0.49
     četiri
    0.49
     scienze
    0.48
     Hallo
    0.48
    POSITIVE LOGITS
    󰀄
    0.57
    Curl
    0.55
     ఇతర
    0.52
     जख
    0.52
    <0xE4>
    0.52
    ВО
    0.52
    скет
    0.51
    Ct
    0.51
    🆚
    0.50
    })
    0.50
    Activations Density 0.005%

    No Known Activations