© 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. 10-GEMMASCOPE-RES-131K
    7. 42162
    Prev
    Next
    INDEX
    Explanations

    9 followed by version numbers or names

    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
     you
    -2.73
     после
    -2.53
     Hinsicht
    -2.48
     ก็
    -2.44
     сентября
    -2.38
    ၉
    -2.33
    งิน
    -2.33
     边框
    -2.30
     Also
    -2.27
     sebelum
    -2.25
    POSITIVE LOGITS
    9
    3.56
    ties
    3.14
    m
    2.95
    裡的
    2.91
    ers
    2.80
    B
    2.78
    T
    2.69
    X
    2.69
    C
    2.66
    P
    2.66
    Activations Density 0.267%

    No Known Activations