© 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. 6936
    Prev
    Next
    INDEX
    Explanations

    other additional

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

    The neuron is keyed to tokens denoting JavaScript file references, i.e. filenames ending in “.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
     superficial
    0.56
    dim
    0.55
    <table>
    0.55
    ですよ
    0.54
     dim
    0.52
     $|
    0.51
    cenie
    0.51
     −
    0.51
    ennan
    0.51
     weakened
    0.50
    POSITIVE LOGITS
    /*
    0.86
    (/*
    0.82
    /*.
    0.78
     <!--<
    0.78
    /*'
    0.77
    ,/*
    0.74
     /*
    0.70
     અન્ય
    0.67
    /*',
    0.65
     તથા
    0.60
    Activations Density 0.005%

    No Known Activations