© 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. 67336
    Prev
    Next
    INDEX
    Explanations

    code delimiters opening

    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
     coû
    -1.48
     kompatibel
    -1.41
     мы
    -1.41
    蓠
    -1.41
     incendios
    -1.41
     renfer
    -1.38
     véhic
    -1.38
    tidak
    -1.37
     réjou
    -1.37
    𝄆
    -1.35
    POSITIVE LOGITS
     for
    2.48
     to
    2.19
     all
    2.11
     by
    1.69
     in
    1.67
     at
    1.64
     on
    1.55
     before
    1.54
     even
    1.54
     as
    1.52
    Activations Density 0.025%

    No Known Activations