© 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. 22203
    Prev
    Next
    INDEX
    Explanations

    directional changes in numbers

    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
     both
    -1.39
     entrambi
    -1.26
    如果
    -1.26
    我们
    -1.23
     beiden
    -1.18
    TONE
    -1.17
    一番
    -1.16
     båda
    -1.16
    espół
    -1.14
    𝐊
    -1.14
    POSITIVE LOGITS
     in
    1.74
    錚
    1.46
     hogy
    1.38
    ㈡
    1.38
     who
    1.37
    後記
    1.30
    逆に
    1.27
     number
    1.27
    ☟
    1.27
     των
    1.26
    Activations Density 0.162%

    No Known Activations