© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22569
    Prev
    Next
    INDEX
    Explanations

    element symbols and numbers

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

    chemical formulas and molecular compounds in scientific texts.

    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
     when
    -1.47
     deudas
    -1.42
    鲧
    -1.38
     bekym
    -1.30
    Πηγές
    -1.27
     velkommen
    -1.27
    of
    -1.27
     in
    -1.26
    in
    -1.25
     because
    -1.25
    POSITIVE LOGITS
    .
    1.61
    Probably
    1.54
    They
    1.53
    Obviously
    1.48
    Their
    1.48
    клады
    1.44
    Compared
    1.43
    Unfortunately
    1.41
    Although
    1.39
    Trying
    1.39
    Activations Density 0.010%

    No Known Activations