© 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. 39928
    Prev
    Next
    INDEX
    Explanations

    config keys and values

    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
     have
    -1.89
    ekw
    -1.80
     為
    -1.78
     來
    -1.71
    蓠
    -1.70
     documented
    -1.63
     Können
    -1.62
     weeks
    -1.62
     painstaking
    -1.61
     inability
    -1.60
    POSITIVE LOGITS
    upport
    1.70
    ttä
    1.70
    sians
    1.68
    to
    1.63
     singh
    1.59
    tividade
    1.56
    🍻
    1.52
     plastiques
    1.52
    he
    1.51
    eration
    1.51
    Activations Density 0.193%

    No Known Activations