© 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. 8385
    Prev
    Next
    INDEX
    Explanations

    Object, Night, court, Cowell

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

    The neuron activates on named entities or other capitalized identifiers (proper nouns and titles).

    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
    m
    -3.33
    c
    -3.02
    v
    -2.64
    6
    -2.52
    p
    -2.50
    ma
    -2.47
    X
    -2.45
    3
    -2.42
    ol
    -2.41
    n
    -2.39
    POSITIVE LOGITS
     interés
    2.20
     zru
    2.11
    ladı
    2.11
     Empieza
    2.06
    韭
    2.05
     ouvido
    2.05
    癀
    2.05
     stalo
    2.02
    kenal
    2.00
     Após
    2.00
    Activations Density 0.125%

    No Known Activations