© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6406
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on very high‐frequency/common words and punctuation tokens (e.g. “it,” “and,” “related,” closing parenthesis), effectively marking common function words and punctuation.

    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_24_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
     kala
    0.84
    iranja
    0.77
    几十
    0.75
    imètres
    0.75
    <0x0E>
    0.73
    ","-
    0.73
     Avid
    0.73
    比如
    0.72
    如下
    0.72
     accentuated
    0.72
    POSITIVE LOGITS
    লে
    0.78
     hermano
    0.71
    hnen
    0.71
     salón
    0.67
     господар
    0.67
     cuentan
    0.66
    ক
    0.66
    কে
    0.64
     hierarchies
    0.64
     જગ્યા
    0.64
    Activations Density 0.000%

    No Known Activations