© 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. 7417
    Prev
    Next
    INDEX
    Explanations

    whole [new/lot/bunch/story/different]

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

    The neuron is a high‐precision detector for the token “whole.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    赑
    -2.55
     continúas
    -2.52
    b
    -2.28
    k
    -2.06
    R
    -2.00
    N
    -2.00
    S
    -1.98
    the
    -1.96
    to
    -1.95
    at
    -1.92
    POSITIVE LOGITS
    ☫
    2.41
    などが
    1.90
    ropractor
    1.90
    霁
    1.90
    Avantages
    1.88
    屉
    1.83
    呖
    1.80
    🗹
    1.77
    ceptibility
    1.73
    鋮
    1.73
    Activations Density 0.004%

    No Known Activations