© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104522
    Prev
    Next
    INDEX
    Explanations

    city, day, user, file

    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
    scryfall
    -0.97
     cuarta
    -0.97
    Če
    -0.96
    ánicos
    -0.95
     programu
    -0.94
    }/${
    -0.94
    bánh
    -0.93
     восстанов
    -0.93
    $^\
    -0.93
    lardan
    -0.93
    POSITIVE LOGITS
     而
    1.04
    there
    0.94
     Therefore
    0.86
     proper
    0.83
    There
    0.82
    !
    0.82
    ,
    0.82
    Regardless
    0.82
     overpriced
    0.81
    Thus
    0.79
    Activations Density 0.171%

    No Known Activations