© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37957
    Prev
    Next
    INDEX
    Explanations

    license terms or versions

    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
     Giugno
    -0.86
     diverso
    -0.82
     Paesi
    -0.80
    umsy
    -0.74
    DO
    -0.73
    不可思议
    -0.73
    électricité
    -0.73
     =>
    -0.73
    RAS
    -0.72
    ”:
    -0.72
    POSITIVE LOGITS
     המ
    0.79
     productive
    0.77
     nom
    0.77
     sumamente
    0.71
     estabilidad
    0.70
     toto
    0.69
     amplification
    0.69
     fries
    0.69
     perimeter
    0.69
     mot
    0.68
    Activations Density 0.005%

    No Known Activations