© 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. 681
    Prev
    Next
    INDEX
    Explanations

    python imports and programming constructs

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

    The neuron fires strongly on programming API or library identifiers (e.g. exception class names, header filenames, package or import paths).

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

    programming package names and file paths in technical documentation.

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

    references to programming code and libraries, including namespaces, file paths, API/package names, and technical error or type identifiers.

    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
     پیسې
    0.80
     व्हिडी
    0.79
    銛
    0.77
    र्यंत
    0.75
     करण्यात
    0.74
     निजामाच्या
    0.73
    ॅम्प
    0.71
     डिपॉ
    0.71
    ॕ
    0.71
     लिहिले
    0.70
    POSITIVE LOGITS
    ↵
    0.90
    ;
    0.90
    ↵↵
    0.84
     as
    0.80
    ↵↵↵
    0.74
     =
    0.72
      
    0.71
     from
    0.69
    0.68
     ;
    0.68
    Activations Density 0.004%

    No Known Activations