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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41008
    Prev
    Next
    INDEX
    Explanations

    bodily fluids, fire, work, or food

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

    technical terms, specialized vocabulary, and objects related to science, technology, and specific domains.

    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_10/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
    ַּ
    -1.89
    ּוֹ
    -1.80
     in
    -1.75
    НОЕ
    -1.59
    -1.54
    }(),
    -1.48
     jorge
    -1.43
     terão
    -1.42
    ogues
    -1.41
     ocasião
    -1.41
    POSITIVE LOGITS
     chré
    1.81
     these
    1.63
     tych
    1.59
    amkeit
    1.58
     religieux
    1.58
     industrias
    1.57
     we
    1.52
     respectivamente
    1.50
     zatím
    1.49
     lámparas
    1.49
    Activations Density 0.120%
    No Known Activations