© 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. 34-GEMMASCOPE-RES-131K
    7. 57206
    Prev
    Next
    INDEX
    Explanations

    file extensions and types

    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
    っちゃった
    -1.01
    儷
    -0.90
    σσ
    -0.88
    ankara
    -0.86
    tovní
    -0.86
     viviendas
    -0.85
    álních
    -0.84
    жні
    -0.84
    ERK
    -0.84
     XXIX
    -0.83
    POSITIVE LOGITS
    苺
    0.99
     HEL
    0.81
     procedimento
    0.81
    。『
    0.79
     animato
    0.77
     NRW
    0.77
    ጻ
    0.77
     imposto
    0.77
     perte
    0.75
    continued
    0.75
    Activations Density 0.006%

    No Known Activations