© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113588
    Prev
    Next
    INDEX
    Explanations

    vary from to

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

    This neuron responds to numeric measurements or statistics (e.g. percentages, counts, or other number tokens).

    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
     from
    -1.41
    }{
    -1.41
    a
    -1.39
    tahu
    -1.37
     estekak
    -1.35
    the
    -1.33
    besondere
    -1.31
    ŚCI
    -1.31
     had
    -1.31
    <bos>
    -1.31
    POSITIVE LOGITS
    遢
    1.57
     plaît
    1.57
    卨
    1.54
    футболка
    1.51
    摃
    1.47
    婳
    1.47
     получает
    1.45
    曏
    1.44
    ブログ村
    1.39
    茑
    1.39
    Activations Density 0.017%

    No Known Activations