© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66207
    Prev
    Next
    INDEX
    Explanations

    things that don't work

    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
    ほんとに
    -1.84
    粜
    -1.82
    extremely
    -1.77
    マジで
    -1.77
    ほんと
    -1.76
    めちゃくちゃ
    -1.76
    あんまり
    -1.72
    すごく
    -1.72
     enorme
    -1.71
     américains
    -1.67
    POSITIVE LOGITS
     or
    2.67
     with
    2.61
     in
    2.34
     for
    2.25
     of
    1.95
     when
    1.91
     on
    1.81
     that
    1.68
     because
    1.63
     With
    1.56
    Activations Density 0.049%

    No Known Activations