© 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. 14876
    Prev
    Next
    INDEX
    Explanations

    go signal or ready status

    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
    endencies
    -1.20
    Sementara
    -1.18
    however
    -1.16
     ちゃ
    -1.15
    ไม่มี
    -1.14
    Tetapi
    -1.12
     aegis
    -1.12
    Identyfik
    -1.10
     mots
    -1.10
     daba
    -1.09
    POSITIVE LOGITS
     that
    1.78
     conseguiu
    1.66
    いいのか
    1.46
     it
    1.43
     sufficient
    1.41
     from
    1.37
     perdeu
    1.37
     dobrze
    1.33
     এর
    1.31
     enough
    1.28
    Activations Density 0.053%

    No Known Activations