© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49805
    Prev
    Next
    INDEX
    Explanations

    multilingual terms or codes

    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_34/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
     well
    -0.87
     club
    -0.83
    UMP
    -0.82
     described
    -0.81
     pulled
    -0.79
     gikk
    -0.78
     still
    -0.75
    ｖ
    -0.75
     she
    -0.74
     desc
    -0.74
    POSITIVE LOGITS
    tività
    0.95
    ceum
    0.94
    ifiers
    0.90
    jemahan
    0.87
     zdarma
    0.83
    気に
    0.83
    öld
    0.82
    ulsions
    0.82
    oubtedly
    0.81
    imeter
    0.81
    Activations Density 0.019%

    No Known Activations