© 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. 34-GEMMASCOPE-RES-131K
    7. 90303
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    The neuron activates on numeric tokens (digits and related punctuation), effectively identifying numbers and decimal values.

    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
    imdi
    -0.87
    観て
    -0.79
     into
    -0.79
     tracts
    -0.76
     Châ
    -0.75
    risas
    -0.74
    ebenarnya
    -0.72
     राज
    -0.71
     nil
    -0.71
     מל
    -0.70
    POSITIVE LOGITS
     kilka
    0.76
     regional
    0.75
     Ten
    0.75
     ten
    0.74
     Paying
    0.73
    Ten
    0.73
     диска
    0.73
    複数の
    0.73
     вме
    0.72
     Disk
    0.72
    Activations Density 0.064%

    No Known Activations