© 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. 58273
    Prev
    Next
    INDEX
    Explanations

    use this 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_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
     Dept
    -0.70
     сверху
    -0.69
    сыз
    -0.68
     communis
    -0.67
     visita
    -0.66
    rm
    -0.66
    compareTo
    -0.65
    Rm
    -0.64
    錆
    -0.63
     evento
    -0.62
    POSITIVE LOGITS
     entière
    0.69
     Rutgers
    0.65
    帝国
    0.65
    alda
    0.65
    MBOL
    0.64
     Bates
    0.64
    HStack
    0.64
    ()?.
    0.63
    chapp
    0.63
    tanda
    0.63
    Activations Density 0.096%

    No Known Activations