© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34951
    Prev
    Next
    INDEX
    Explanations

    records, seasons, league

    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
     only
    -1.48
     your
    -1.24
    opheles
    -1.19
     '{@
    -1.19
    🪛
    -1.16
    omalies
    -1.13
    息子
    -1.11
    皆さま
    -1.09
    そういえば
    -1.09
    ANIEL
    -1.09
    POSITIVE LOGITS
    k
    1.30
    g
    1.27
    h
    1.27
    ba
    1.27
    kos
    1.26
    b
    1.20
    有一定
    1.18
     farklı
    1.16
    so
    1.13
    ko
    1.13
    Activations Density 0.003%

    No Known Activations