© 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. 34-GEMMASCOPE-RES-131K
    7. 109817
    Prev
    Next
    INDEX
    Explanations

    W.D. or E.D. districts

    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_34/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
     учреждения
    -0.83
    ähteet
    -0.83
    ändern
    -0.79
     mamma
    -0.79
    =.
    -0.78
    帝
    -0.76
    油
    -0.75
     Öl
    -0.74
    君
    -0.74
     Rud
    -0.73
    POSITIVE LOGITS
     Texas
    0.78
     docket
    0.78
     Louisiana
    0.76
    닙
    0.74
     Michigan
    0.73
    handlung
    0.72
    nasium
    0.70
    感的
    0.69
    的一天
    0.69
     of
    0.68
    Activations Density 0.097%

    No Known Activations