© 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. 10-GEMMASCOPE-RES-131K
    7. 43573
    Prev
    Next
    INDEX
    Explanations

    Provost, Provo, Commandant

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

    This neuron activates on capitalized “Prov-” words—e.g. “Provost” and “Provo.”

    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
    ⟞
    -2.52
     your
    -2.52
    ⟝
    -2.44
    튿
    -2.34
    羮
    -2.31
    jenigen
    -2.23
    没关系
    -2.20
    嶮
    -2.16
     pomysł
    -2.14
    找个
    -2.11
    POSITIVE LOGITS
     et
    2.47
    ⤞
    2.38
    愎
    2.27
     of
    2.25
    ↵
    2.13
    ’
    2.11
    ቍ
    2.08
    цию
    2.05
    ;
    1.97
    婞
    1.95
    Activations Density 0.002%

    No Known Activations