© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6567
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric tokens representing quantities (e.g. counts, percentages, thresholds, large numerical values).

    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_31_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
    bergement
    0.64
    ោម
    0.56
     үй
    0.56
    aspetto
    0.55
     裏
    0.54
    ummies
    0.54
     gọn
    0.54
     वितरित
    0.54
    itettura
    0.54
     новогод
    0.54
    POSITIVE LOGITS
     threshold
    2.63
     thresholds
    2.55
    threshold
    2.47
    Threshold
    2.27
     Threshold
    2.27
    阈
    2.23
     thresh
    2.02
    閾
    1.99
    THRESHOLD
    1.93
    thresh
    1.91
    Activations Density 0.648%

    No Known Activations