© 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. 22-GEMMASCOPE-RES-131K
    7. 84047
    Prev
    Next
    INDEX
    Explanations

    semicolon

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

    This neuron fires on tokens containing digits—that is, numeric literals or numbers embedded in identifiers (e.g. version numbers, numeric constants, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Autó
    -1.27
    huevos
    -1.06
    yyb
    -1.03
    isini
    -1.01
    Kolor
    -0.99
    paisaje
    -0.99
    tarta
    -0.98
    espejo
    -0.97
     kabát
    -0.96
    
    -0.95
    POSITIVE LOGITS
    N
    1.00
    o
    0.96
    P
    0.94
    k
    0.94
    Y
    0.91
    0.91
    D
    0.88
    L
    0.88
    S
    0.88
    J
    0.88
    Activations Density 0.014%
    No Known Activations