© 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. 74320
    Prev
    Next
    INDEX
    Explanations

    monocrotaline, acrylamide, Acroceridae, LACROIX

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

    chemical compound names and scientific terminology.

    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
    The
    -2.91
    我们
    -2.50
    ſelf
    -2.33
     It
    -2.33
    棪
    -2.31
    ст
    -2.23
    …’
    -2.16
     Psicología
    -2.16
     However
    -2.16
    ים
    -2.16
    POSITIVE LOGITS
    0
    3.86
    w
    2.73
    3
    2.63
    i
    2.59
    a
    2.50
    section
    2.44
    2.41
     '
    2.38
     edifici
    2.36
    ↵
    2.19
    Activations Density 0.037%

    No Known Activations