© 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. 106524
    Prev
    Next
    INDEX
    Explanations

    . following words

    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
     geno
    -0.81
    dues
    -0.78
    faker
    -0.73
    omal
    -0.73
     teat
    -0.70
    ureux
    -0.69
     Ephraim
    -0.69
     victories
    -0.68
     motherfucker
    -0.68
    TALL
    -0.68
    POSITIVE LOGITS
     móds
    0.77
    вѣ
    0.76
    дѣ
    0.75
     ΤΟ
    0.73
     Архи
    0.71
     horizon
    0.70
     בעל
    0.70
     verbeteren
    0.69
     Enforcement
    0.69
    reciation
    0.69
    Activations Density 0.022%

    No Known Activations