© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86807
    Prev
    Next
    INDEX
    Explanations

    Cory, Dopaminergic, SqlParameter

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

    The neuron selectively fires on capitalized identifiers and proper nouns—e.g. class or type names in code and names of people or entities in text.

    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
    -3.31
    i
    -3.02
     -
    -2.88
    ing
    -2.66
    );
    -2.66
    3
    -2.59
    仅仅
    -2.59
     '
    -2.58
    ),
    -2.50
     )
    -2.48
    POSITIVE LOGITS
    dzić
    3.33
    婞
    2.84
     garganta
    2.61
    ۠
    2.59
    了一个
    2.58
     santé
    2.44
    щему
    2.39
    Lire
    2.38
     помогает
    2.30
    孥
    2.27
    Activations Density 0.006%

    No Known Activations