© 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. 34-GEMMASCOPE-RES-131K
    7. 49086
    Prev
    Next
    INDEX
    Explanations

    colors and materials as accents

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

    The neuron fires on tokens that are (parts of) numbers or numeric expressions (e.g. digit sequences and units).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    EventId
    -0.84
     WARRANTIES
    -0.77
     очеред
    -0.75
    ^{-}
    -0.75
     éti
    -0.75
    ('/:
    -0.74
    ܂
    -0.74
     verz
    -0.73
    advanced
    -0.72
    äler
    -0.72
    POSITIVE LOGITS
     accents
    3.23
     accent
    2.67
     Accent
    2.11
    Accent
    2.06
    accent
    2.06
     trim
    1.96
     highlights
    1.78
     accented
    1.60
    アクセント
    1.50
     contrast
    1.49
    Activations Density 0.042%

    No Known Activations