Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11571
    Prev
    Next
    INDEX
    Explanations

    every type of

    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_22/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
     trám
    -1.43
     花纹
    -1.35
    趼
    -1.31
     mojej
    -1.30
     内衣
    -1.30
    婓
    -1.22
    糴
    -1.20
     手绘
    -1.19
     rô
    -1.16
    ܇
    -1.16
    POSITIVE LOGITS
     you
    1.64
     of
    1.61
     these
    1.60
     every
    1.56
     that
    1.48
     those
    1.28
     make
    1.25
     in
    1.23
     Every
    1.18
     Incluso
    1.14
    Activations Density 0.026%

    No Known Activations