© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128154
    Prev
    Next
    INDEX
    Explanations

    medical terms, technical descriptions, and specific nouns

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

    proper nouns and abbreviations, particularly names of people, organizations, and technical terms.

    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
     [
    -1.09
    mographie
    -0.99
     exakt
    -0.98
     Während
    -0.97
     Chriftian
    -0.96
     Majefty
    -0.96
     vielleicht
    -0.94
     occaf
    -0.94
     poffible
    -0.93
     sämtliche
    -0.93
    POSITIVE LOGITS
     készült
    1.03
    ому
    0.99
    снимок
    0.96
    ‌.
    0.96
    НІ
    0.95
     relevance
    0.93
    略歴
    0.92
    颯
    0.92
     expended
    0.91
     any
    0.90
    Activations Density 0.024%

    No Known Activations