© 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. 22-GEMMASCOPE-RES-131K
    7. 65942
    Prev
    Next
    INDEX
    Explanations

    numbers followed by HP, Signals, Binary

    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_22/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
     další
    -1.27
    鞴
    -1.17
     cland
    -1.13
    
    -1.13
    bosky
    -1.13
    lägen
    -1.10
    鋮
    -1.10
    asztok
    -1.09
     desgra
    -1.08
     sonriente
    -1.08
    POSITIVE LOGITS
     of
    1.44
     in
    1.34
    s
    1.33
     as
    1.30
     on
    1.25
    m
    1.21
    c
    1.15
    w
    1.14
    H
    1.13
         
    1.07
    Activations Density 0.134%

    No Known Activations