© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130797
    Prev
    Next
    INDEX
    Explanations

    bioactive compounds and deprecated protocols

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

    words related to documentation, particularly "handouts" and "deprecated" items.

    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
    _
    -3.23
    -
    -3.13
    </em>
    -2.80
    z
    -2.63
    y
    -2.47
    m
    -2.44
    o
    -2.42
     gewisser
    -2.42
    ㉗
    -2.28
     erheblich
    -2.27
    POSITIVE LOGITS
    besondere
    2.61
    怎么能
    2.56
     LIKE
    2.55
    褔
    2.42
    してました
    2.30
    軚
    2.28
    니메이션
    2.28
    ？】
    2.27
    还真是
    2.25
    딪
    2.23
    Activations Density 0.008%

    No Known Activations