© 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. 9553
    Prev
    Next
    INDEX
    Explanations

    people and places

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

    This neuron activates on parts of proper names (i.e. tokens belonging to named entities).

    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
    鲥
    -2.73
     ответил
    -2.50
     řekl
    -2.42
    骜
    -2.39
     复古
    -2.34
    ㈯
    -2.34
    pumpe
    -2.30
    KommentareTeilen
    -2.25
    isés
    -2.22
     ////
    -2.22
    POSITIVE LOGITS
    Y
    3.47
    ”
    3.27
    an
    3.27
    M
    3.23
    in
    3.02
    D
    3.02
    that
    2.98
    P
    2.92
    by
    2.91
    ↵
    2.88
    Activations Density 0.080%

    No Known Activations