© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38915
    Prev
    Next
    INDEX
    Explanations

    vice president for, director of

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

    This neuron detects organizational role or job‐title phrases (e.g. “vice president,” “director,” “chief constable,” etc.).

    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
     Verlauf
    -1.38
    N
    -1.31
     estrema
    -1.29
    為に
    -1.27
    A
    -1.25
    X
    -1.25
    R
    -1.24
    V
    -1.23
    Q
    -1.23
     $
    -1.22
    POSITIVE LOGITS
     in
    1.89
     and
    1.53
     at
    1.40
    內容簡介
    1.34
     for
    1.24
    𖧵
    1.22
    และ
    1.20
    ølge
    1.20
     án
    1.17
    前は
    1.17
    Activations Density 0.015%

    No Known Activations