© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    css border and margin properties

    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
    কার
    -0.88
    ﾔ
    -0.83
    ansvar
    -0.83
    utian
    -0.80
     dovol
    -0.79
     আর
    -0.79
    CLUYE
    -0.77
    ⵜ
    -0.77
    ToBounds
    -0.77
    kaper
    -0.77
    POSITIVE LOGITS
    -
    1.27
    Bottom
    0.84
    left
    0.81
    Left
    0.80
    ỡ
    0.79
     reizen
    0.73
     Ediciones
    0.73
     ?”
    0.73
    ={()
    0.71
     coronav
    0.71
    Activations Density 0.146%

    No Known Activations