© 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. 130192
    Prev
    Next
    INDEX
    Explanations

    group names, acronyms, code snippets

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

    The neuron is tuned to single tokens representing proper nouns or other title-cased “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
    1
    -3.66
    ↵↵
    -3.00
     
    -2.92
    ⏑
    -2.77
    🡺
    -2.72
     $
    -2.55
    鈊
    -2.41
    让他
    -2.39
     {
    -2.39
    </em>
    -2.28
    POSITIVE LOGITS
    ’
    3.73
    ⦊
    2.70
    ଞ
    2.55
     utilizzati
    2.53
     realizzata
    2.52
     proposito
    2.50
     العالمية
    2.48
     riservata
    2.48
     scritta
    2.47
    体は
    2.47
    Activations Density 0.007%

    No Known Activations