© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111909
    Prev
    Next
    INDEX
    Explanations

    wrought iron fence

    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_10/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
    𖥧
    -3.00
    er
    -2.97
    ية
    -2.73
    \
    -2.55
    medriver
    -2.48
    早已
    -2.34
    most
    -2.30
     hinder
    -2.28
     This
    -2.25
    9
    -2.22
    POSITIVE LOGITS
     Díaz
    2.14
     matériau
    2.06
     aliments
    2.02
     caro
    2.00
     greateſt
    1.98
    ické
    1.94
     hindi
    1.93
     BIBLIOGRAPHY
    1.91
     methode
    1.89
     菇
    1.89
    Activations Density 0.010%

    No Known Activations