© 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. 12200
    Prev
    Next
    INDEX
    Explanations

    Activision, Divesting

    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
    ׇ
    -1.09
    ⫹
    -1.00
     their
    -0.99
     should
    -0.96
     often
    -0.96
    scrollY
    -0.95
     all
    -0.94
     most
    -0.93
    Win
    -0.93
    dienne
    -0.92
    POSITIVE LOGITS
     vinaigre
    1.21
    fficking
    1.16
    Ndr
    1.12
    Irak
    1.11
    chymal
    1.10
     タワー
    1.09
     饼
    1.09
     casó
    1.06
    亵
    1.05
     препарат
    1.05
    Activations Density 0.000%

    No Known Activations