© 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. 58816
    Prev
    Next
    INDEX
    Explanations

    not a fan of

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

    This neuron detects expressions of personal preference phrased with “fan” (e.g. “not a fan of,” “huge fan of,” “big fan of”).

    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
    既に
    -1.24
    寝る
    -1.23
     bereits
    -1.17
     Weizen
    -1.17
     that
    -1.16
    そのような
    -1.13
    なんだろう
    -1.12
    一緒
    -1.11
    けれど
    -1.10
     informatique
    -1.09
    POSITIVE LOGITS
    ഫ
    1.27
    jsoup
    1.23
    hazel
    1.23
    %",
    1.20
    geordneten
    1.19
     geschenk
    1.19
    ريم
    1.19
    mountable
    1.18
    thma
    1.18
    یا
    1.18
    Activations Density 0.032%

    No Known Activations