© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14832
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (e.g. page/volume numbers, measurements, counts) – in other words, it’s a number‐detector.

    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
     större
    0.76
     Vertrieb
    0.73
     toată
    0.73
     INNOV
    0.72
    իր
    0.71
     गट
    0.71
    껏
    0.71
    літы
    0.71
    igt
    0.70
    ată
    0.69
    POSITIVE LOGITS
    a
    0.86
    o
    0.75
    जीलैंड
    0.75
     界
    0.72
     lectus
    0.72
    ی
    0.72
     ず
    0.71
    ども
    0.70
     لیګ
    0.70
    esas
    0.68
    Activations Density 0.000%

    No Known Activations