© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13004
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on any token that’s part of or directly adjacent to a numeric or value‐like expression. In other words, it detects references to numbers or quantities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ساس
    0.75
    )++;
    0.74
    навли
    0.72
    ilidad
    0.71
    arks
    0.69
     그러나
    0.68
     टोक
    0.68
    uslararası
    0.67
    oyed
    0.67
     യ
    0.66
    POSITIVE LOGITS
    Nearest
    0.72
     stent
    0.72
    郷
    0.71
    та
    0.70
    ၵ
    0.70
     caratteristiche
    0.70
    蕭
    0.69
    Не
    0.69
    ◌
    0.69
    Ле
    0.68
    Activations Density 0.000%

    No Known Activations