© 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. 72897
    Prev
    Next
    INDEX
    Explanations

    people or groups with actions

    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
    futbolista
    -1.16
     it
    -1.15
     there
    -1.14
     in
    -1.05
     gesamten
    -0.97
     kanad
    -0.96
     balón
    -0.95
    calciatore
    -0.95
     mín
    -0.94
     mág
    -0.94
    POSITIVE LOGITS
     ścian
    1.38
     виправи
    1.15
     сможет
    1.11
     tył
    1.10
     warum
    1.05
     niebies
    1.02
    беріга
    1.02
    ༘
    1.02
     számára
    1.02
     thofe
    1.02
    Activations Density 0.001%

    No Known Activations