© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12274
    Prev
    Next
    INDEX
    Explanations

    respectively, mutations, Alcohol, measurement

    np_acts-logits-general · gemini-2.5-flash-lite

    code formatting and indentation in programming files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     to
    -1.33
     by
    -1.30
     any
    -1.14
     it
    -1.12
    DataLoader
    -1.11
     if
    -1.10
     after
    -1.09
     because
    -1.07
     or
    -1.00
     LCCN
    -1.00
    POSITIVE LOGITS
     respectivement
    1.15
     respectively
    1.05
    respectively
    1.00
     essas
    0.96
    這些
    0.93
    inin
    0.91
     первых
    0.88
     einzeln
    0.88
     cias
    0.87
     elevación
    0.86
    Activations Density 0.001%

    No Known Activations