© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130182
    Prev
    Next
    INDEX
    Explanations

    forceful actions and emphasis

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

    The neuron fires on words derived from “force,” spotting coercive or power-related terms (e.g. forcefully, forcibly, force).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {
    -3.20
    ?
    -2.70
    !
    -2.69
    a
    -2.42
    as
    -2.33
    ...
    -2.25
     ``
    -2.20
    .
    -2.19
     como
    -2.09
    in
    -2.08
    POSITIVE LOGITS
    齶
    2.67
    𓐍
    2.27
     geprü
    2.27
    iſe
    2.25
    簟
    2.20
    骝
    2.20
     erhi
    2.17
    棪
    2.16
    齤
    2.14
    derdag
    2.11
    Activations Density 0.002%

    No Known Activations