© 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. 14961
    Prev
    Next
    INDEX
    Explanations

    sort order or size

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

    The neuron activates on floating‐point numeric tokens (decimal number 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_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
    ib
    0.82
    /
    0.73
    </td>
    0.73
     political
    0.73
    大约
    0.73
    ຮ
    0.70
     Acting
    0.70
    -
    0.70
    खु
    0.70
     party
    0.69
    POSITIVE LOGITS
     такую
    0.95
    долго
    0.95
     Embora
    0.95
     обслуживание
    0.94
     adequado
    0.93
    㥉
    0.92
     elegantes
    0.91
     возника
    0.91
     достига
    0.91
     такие
    0.90
    Activations Density 0.000%

    No Known Activations