© 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. 22-GEMMASCOPE-RES-131K
    7. 80048
    Prev
    Next
    INDEX
    Explanations

    `Search` to `results`, `Sin` to `opia`, `Robert` to `Wynne`

    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
    ñora
    -1.15
    虜
    -1.13
    癖
    -1.04
     gneiss
    -1.03
     Ministro
    -1.02
    但却
    -1.02
    calaure
    -1.02
    ремен
    -1.00
    それから
    -1.00
    人員
    -0.99
    POSITIVE LOGITS
    すっ
    1.22
     segnal
    1.16
    genodigd
    1.15
    為に
    1.14
    のではなく
    1.08
    感じで
    1.08
    íe
    1.08
     avendo
    1.07
     conferma
    1.05
    ()<<
    1.04
    Activations Density 0.000%

    No Known Activations