© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13462
    Prev
    Next
    INDEX
    Explanations

    HTML style declarations

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

    The neuron selectively activates on punctuation marks and special symbols commonly found in code or technical syntax (e.g. colons, periods, hyphens, file‐extension tokens like “.js”).

    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
    >//
    0.59
    atsiya
    0.59
    agnie
    0.59
    ];//
    0.59
     वेळा
    0.58
    ');//
    0.55
     दिर
    0.55
     //
    0.54
    ńskich
    0.54
    ابة
    0.54
    POSITIVE LOGITS
     /*
    1.22
    /*
    1.20
    /*.
    0.75
    ,/*
    0.71
    (/*
    0.68
    /*'
    0.66
    /*!
    0.63
    /****
    0.63
     /**
    0.62
    ]/*
    0.60
    Activations Density 0.011%

    No Known Activations