© 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. 128759
    Prev
    Next
    INDEX
    Explanations

    code and comments

    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
     our
    -2.13
     parachoque
    -2.09
     the
    -2.08
    躂
    -1.99
     adil
    -1.89
    桄
    -1.83
    เกง
    -1.80
    besondere
    -1.78
     this
    -1.77
     podes
    -1.75
    POSITIVE LOGITS
     
    2.20
    4
    1.98
     -
    1.88
     are
    1.83
     would
    1.74
     in
    1.73
    /
    1.73
     again
    1.71
    1
    1.70
     Again
    1.67
    Activations Density 0.061%

    No Known Activations