© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1818
    Prev
    Next
    INDEX
    Explanations

    museumdatasetsecholegends

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

    This neuron activates on tokens representing decimal‐formatted numbers (floating‐point numerics).

    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
     क्रिएट
    0.93
    ваю
    0.88
     micrófono
    0.88
     Continuando
    0.84
     टेंपरे
    0.84
     элемент
    0.82
    ディスク
    0.81
    <unused2121>
    0.81
     hermoso
    0.79
     Comptes
    0.79
    POSITIVE LOGITS
     antics
    0.77
     *
    0.75
     vil
    0.75
    vil
    0.73
    ov
    0.73
    0.71
    rr
    0.70
     (
    0.70
     r
    0.70
    spaper
    0.70
    Activations Density 0.001%

    No Known Activations