© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 78
    Prev
    Next
    INDEX
    Explanations

    starts with or followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ATION
    -2.63
    fiable
    -2.61
    嬋
    -2.53
    ﹶ
    -2.53
     温泉
    -2.53
     informar
    -2.52
     uživ
    -2.48
    izzazione
    -2.47
    哢
    -2.47
     miljoen
    -2.45
    POSITIVE LOGITS
    -
    4.50
    ).
    4.13
    1
    3.30
    =
    3.22
    o
    3.08
    ?
    3.06
     [
    2.97
    _
    2.84
    %
    2.81
    –
    2.72
    Activations Density 0.000%

    No Known Activations