© 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. 22-GEMMASCOPE-RES-131K
    7. 15405
    Prev
    Next
    INDEX
    Explanations

    document revision status

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

    The neuron detects document revision markers, specifically instances of “Revision” or “Revised.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ↵↵
    -3.98
    \
    -3.11
    /
    -2.78
    0
    -2.77
    "
    -2.44
    %
    -2.38
    at
    -2.17
     are
    -2.16
    不是很
    -2.16
     aparición
    -2.02
    POSITIVE LOGITS
    鈇
    2.73
    𞤢
    2.48
    莢
    2.28
    ❗
    2.20
     obed
    2.19
     tył
    2.16
    𐐪
    2.14
    ڧ
    2.14
    谞
    2.13
    🚒
    2.11
    Activations Density 0.005%

    No Known Activations