© 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. 20169
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     Deel
    -1.43
     宫
    -1.38
     toolStrip
    -1.36
    σιν
    -1.34
     mika
    -1.33
     jesús
    -1.32
     koch
    -1.30
    listBox
    -1.28
     OXFORD
    -1.26
    够了
    -1.25
    POSITIVE LOGITS
     We
    1.35
     h
    1.29
     H
    1.26
     из
    1.23
    Externí
    1.20
    We
    1.19
     m
    1.17
    Our
    1.16
     our
    1.13
     Our
    1.13
    Activations Density 0.010%

    No Known Activations