© 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. 72440
    Prev
    Next
    INDEX
    Explanations

    Frankie, Zeb, Chel, WK

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

    The neuron activates on capitalized proper nouns—names of people, places, species, or organizations.

    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
    \
    -5.38
    ↵
    -4.25
    0
    -3.48
    }
    -3.22
    ”
    -3.13
    ?
    -2.75
    ’
    -2.69
    <em>
    -2.67
     ‘’
    -2.45
    in
    -2.36
    POSITIVE LOGITS
    𖣔
    2.55
    なのは
    2.55
    なが
    2.53
     erhi
    2.52
     richten
    2.50
    焿
    2.50
     разнообраз
    2.47
    媄
    2.45
    荅
    2.45
    莇
    2.44
    Activations Density 0.016%

    No Known Activations