© 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. 22398
    Prev
    Next
    INDEX
    Explanations

    names and specific entities

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

    This neuron selectively fires on specific named entities and technical terms (e.g. proper nouns, specialized domain names, gene or protocol names).

    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
    -3.19
    '
    -2.84
    <
    -2.52
    ',
    -2.50
    简称
    -2.45
    ală
    -2.45
     be
    -2.34
    acyjny
    -2.34
     estekak
    -2.31
    </td>
    -2.27
    POSITIVE LOGITS
    焢
    2.66
    1
    2.63
    垰
    2.53
    笑话
    2.47
     спросил
    2.42
    
    2.38
    ︐
    2.38
     suporta
    2.27
     ответил
    2.25
     Primarily
    2.25
    Activations Density 0.104%
    No Known Activations