© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59143
    Prev
    Next
    INDEX
    Explanations

    `usually occurs` or `normal`

    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
     veya
    -1.80
    或者
    -1.71
    หรือ
    -1.55
    杈
    -1.53
     vatten
    -1.49
     résultats
    -1.49
     élus
    -1.49
    为啥
    -1.42
     atau
    -1.42
     of
    -1.42
    POSITIVE LOGITS
     also
    2.39
     have
    1.98
     as
    1.91
     For
    1.89
     get
    1.88
     take
    1.79
     so
    1.70
     no
    1.70
     well
    1.67
     not
    1.66
    Activations Density 0.239%

    No Known Activations