© 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. 22162
    Prev
    Next
    INDEX
    Explanations

    moderator or anesthesia

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

    words related to forum or meeting roles, particularly "moderator" and similar leadership positions.

    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
    a
    -3.73
    胧
    -3.33
    鹛
    -3.03
    鼍
    -2.86
    the
    -2.58
    ႐
    -2.53
    鯪
    -2.47
    ludes
    -2.47
    carnated
    -2.42
     :).
    -2.33
    POSITIVE LOGITS
    section
    2.44
    PAIGN
    2.31
    Publié
    2.28
    開始
    2.25
     puzzled
    2.19
    Despite
    2.17
    </i>
    2.16
    繾
    2.11
    And
    2.09
    Being
    2.09
    Activations Density 0.020%

    No Known Activations