© 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. 9972
    Prev
    Next
    INDEX
    Explanations

    matrix notation

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

    The neuron strongly activates on tokens that are decimal‐formatted numbers (i.e., floating‐point numeric 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
    ف
    0.82
     montagna
    0.79
     montaña
    0.79
     는
    0.78
     भीड़
    0.77
     Anche
    0.76
    íng
    0.76
     comun
    0.76
     molti
    0.75
     circun
    0.75
    POSITIVE LOGITS
    ile
    0.76
    and
    0.70
    delete
    0.69
    ar
    0.68
    ase
    0.68
    */
    0.68
     Gant
    0.68
    up
    0.68
     iterator
    0.68
    PLUS
    0.68
    Activations Density 0.000%

    No Known Activations