© 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. 63173
    Prev
    Next
    INDEX
    Explanations

    configuration text or code

    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
    괴
    -0.68
    嚏
    -0.68
     shorter
    -0.66
     usurp
    -0.65
     Advisor
    -0.64
    ubov
    -0.63
    最新的
    -0.63
     calling
    -0.62
     twenty
    -0.62
    НЯ
    -0.61
    POSITIVE LOGITS
    ECD
    0.71
     Speise
    0.68
     Emerson
    0.67
    elezo
    0.65
    escalier
    0.64
     Xe
    0.64
    Futures
    0.63
     Pyrr
    0.63
     Cud
    0.62
    enservice
    0.62
    Activations Density 0.067%

    No Known Activations