© 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. 60830
    Prev
    Next
    INDEX
    Explanations

    synergistic activation and effects

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

    words like "Kohnstamm", "Hallelujah", and "synergistic" - scientific terms or specific proper nouns that appear in technical or specialized contexts.

    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
    ’
    -3.11
    i
    -2.64
     That
    -2.56
     Also
    -2.53
     utter
    -2.48
     Our
    -2.41
     agonizing
    -2.39
    имость
    -2.38
    e
    -2.38
     zahlreiche
    -2.34
    POSITIVE LOGITS
    \
    2.63
     soldado
    2.63
    Ꝑ
    2.48
     wenn
    2.42
    ຝ
    2.41
    ">
    2.30
    垕
    2.30
     foram
    2.27
    跸
    2.23
    多人
    2.17
    Activations Density 0.043%

    No Known Activations