© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11476
    Prev
    Next
    INDEX
    Explanations

    allow

    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
    ’
    -3.03
    end
    -2.83
    ar
    -2.48
    i
    -2.39
    ,
    -2.27
    螄
    -2.20
    ir
    -2.13
    𐍆
    -2.11
    (
    -2.08
    you
    -2.06
    POSITIVE LOGITS
    焄
    2.42
    妘
    2.16
     BEFORE
    2.09
    wirkt
    2.06
    他们是
    2.06
    formación
    2.00
    scription
    1.99
    つけた
    1.98
    न
    1.97
     Países
    1.96
    Activations Density 0.017%

    No Known Activations