© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112641
    Prev
    Next
    INDEX
    Explanations

    IgE antibody

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

    specialized technical terms or proper nouns within different fields, particularly those related to science, programming, and gaming.

    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
    </u>
    -2.75
    3
    -2.41
    2
    -2.36
    5
    -2.31
    8
    -2.23
     tatuajes
    -2.20
    4
    -2.17
    0
    -2.17
    9
    -2.13
    7
    -2.06
    POSITIVE LOGITS
    </h2>
    2.58
    OUTUBE
    2.45
    塒
    1.91
    🛇
    1.85
    平常
    1.85
    ホルダー
    1.80
    pters
    1.73
     ܙ
    1.73
    燹
    1.71
    徧
    1.66
    Activations Density 0.005%

    No Known Activations