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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10396
    Prev
    Next
    INDEX
    Explanations

    code delimiters and comments

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

    The neuron is triggered by numeric tokens (numbers or number-like strings) in the text.

    oai_token-act-pair · o4-miniTriggered 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
     such
    0.59
     estará
    0.58
     继续访问
    0.56
    లంగా
    0.55
     beat
    0.54
     F
    0.54
     menores
    0.53
     Beat
    0.52
     ఒకటి
    0.50
     தா
    0.50
    POSITIVE LOGITS
    //
    2.16
     //
    1.98
    ;//
    1.76
    ();//
    1.73
    ,//
    1.69
    ];//
    1.68
    ++;//
    1.65
    ]//
    1.62
     {//
    1.59
    );//
    1.54
    Activations Density 0.023%

    No Known Activations