© 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. 22-GEMMASCOPE-RES-131K
    7. 13393
    Prev
    Next
    INDEX
    Explanations

    Node.js related code

    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
    e
    -2.41
     vorigen
    -2.27
    ’
    -2.25
    vantaged
    -2.20
    けど
    -2.19
    しました
    -2.16
    y
    -2.14
     wodurch
    -2.13
    o
    -2.05
    .”
    -2.03
    POSITIVE LOGITS
    \
    3.31
    翆
    2.75
    ра
    2.61
     alemán
    2.41
    大多
    2.41
     citado
    2.30
     améli
    2.28
     '
    2.27
    早晨
    2.25
     enfermos
    2.23
    Activations Density 0.034%

    No Known Activations