© 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. 22-GEMMASCOPE-RES-131K
    7. 72946
    Prev
    Next
    INDEX
    Explanations

    variable names and identifiers

    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_22/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
     what
    -1.22
     it
    -1.12
    Nearly
    -1.03
     which
    -1.03
    Earlier
    -0.99
     What
    -0.97
     key
    -0.97
    いえば
    -0.97
    Many
    -0.96
    Some
    -0.94
    POSITIVE LOGITS
     سيارة
    1.05
    naments
    0.94
    рка
    0.93
    𓆏
    0.92
     entram
    0.92
    -<
    0.91
     Merlot
    0.89
     deras
    0.89
    ̂
    0.88
    licitations
    0.87
    Activations Density 0.046%

    No Known Activations