© 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. 40459
    Prev
    Next
    INDEX
    Explanations

    evaluation, innovation, health, basis, nature

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

    academic or scientific concepts and terminology in formal documents or papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags the main “headline” or title words (especially the key nouns and the “X of” pattern) you see in academic‐style section or paper titles.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     at
    -2.69
     in
    -2.52
     on
    -2.50
     with
    -2.41
     just
    -2.17
     because
    -2.14
     if
    -2.13
     for
    -1.97
     There
    -1.95
     when
    -1.95
    POSITIVE LOGITS
     Dinas
    1.77
    𓆏
    1.74
    ఽ
    1.73
     💕
    1.73
     WIL
    1.68
     INDIA
    1.68
    甞
    1.67
    ㅐ
    1.66
     BEN
    1.66
     xvi
    1.63
    Activations Density 0.182%

    No Known Activations