© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110892
    Prev
    Next
    INDEX
    Explanations

    numbers followed by points or percentages

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

    The neuron activates on numeric tokens and number-related expressions (digits, numerals, and words representing quantities).

    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
    avista
    -0.75
     Partial
    -0.74
    igur
    -0.73
    toto
    -0.73
     criticism
    -0.73
    Barnes
    -0.72
     artigian
    -0.72
    minutos
    -0.71
    üre
    -0.71
    irá
    -0.69
    POSITIVE LOGITS
     points
    1.73
    points
    1.49
     percentage
    1.44
    point
    1.42
     point
    1.39
    ポイント
    1.12
    Points
    1.09
     Points
    1.03
     pp
    1.02
     puntos
    1.02
    Activations Density 0.040%

    No Known Activations