© 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. 22-GEMMASCOPE-RES-131K
    7. 71927
    Prev
    Next
    INDEX
    Explanations

    research and independent sources

    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
     those
    -1.34
     many
    -1.21
     first
    -1.16
     itens
    -1.10
     some
    -1.10
    Despite
    -1.09
     शुर
    -1.09
     extraordinarily
    -1.09
     penjualan
    -1.07
     epitom
    -1.06
    POSITIVE LOGITS
     dando
    1.24
     independente
    1.23
    ficie
    1.16
     Dinas
    1.15
    diert
    1.13
     extravag
    1.12
    izione
    1.11
     可愛い
    1.09
    PARTE
    1.07
     intric
    1.05
    Activations Density 0.031%

    No Known Activations