© 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. 85882
    Prev
    Next
    INDEX
    Explanations

    same name or around the corner

    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
     with
    -2.16
     and
    -2.02
     by
    -1.95
     on
    -1.84
     from
    -1.82
     a
    -1.68
     in
    -1.58
     for
    -1.52
     their
    -1.50
     of
    -1.45
    POSITIVE LOGITS
     toallas
    1.73
    brtc
    1.45
     heridas
    1.43
    Ketika
    1.39
    ⌵
    1.38
    mann
    1.38
    ⸢
    1.35
     logros
    1.34
    Tetapi
    1.32
     bolsillos
    1.31
    Activations Density 0.181%

    No Known Activations