© 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. 72780
    Prev
    Next
    INDEX
    Explanations

    age and background

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

    The neuron fires on numeric or quantitative attribute tokens—e.g. sizes, ages, specifications, measures, calibers—indicating it detects mentions of numbers or measurable properties.

    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
    borderSide
    -1.53
     alcune
    -1.48
     leone
    -1.48
     auffi
    -1.47
     territo
    -1.43
     moeili
    -1.42
     hilfiger
    -1.39
    ‛
    -1.34
    delà
    -1.31
     semacam
    -1.30
    POSITIVE LOGITS
    ;
    1.50
     ANY
    1.44
    .
    1.32
     urges
    1.21
    任何
    1.21
     интел
    1.19
     Nachfrage
    1.17
    =
    1.16
     ;
    1.15
     (
    1.14
    Activations Density 0.077%

    No Known Activations