© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5080
    Prev
    Next
    INDEX
    Explanations

    `(`

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

    The neuron activates on tokens that contain numeric characters—e.g. IDs, indices, or identifiers with digits.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    饋
    0.58
    reward
    0.57
    ต่อไป
    0.57
    ведена
    0.56
    Reward
    0.54
    cmb
    0.54
    ßerdem
    0.50
     इनको
    0.50
    спеди
    0.50
    adeo
    0.50
    POSITIVE LOGITS
    )^{
    1.46
    )[
    1.45
    )^
    1.43
    )['
    1.40
    ).^
    1.30
    )^{\
    1.30
    ')[
    1.30
    )^\
    1.29
    )²
    1.27
    )["
    1.27
    Activations Density 0.020%

    No Known Activations