© 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. 3212
    Prev
    Next
    INDEX
    Explanations

    comparisons and distinctions

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

    This neuron is highly activated by numeric tokens, especially floating‐point values and other in‐text numbers (e.g. measurements, ISBNs, statistical figures).

    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
     L
    0.80
     Л
    0.79
     ECO
    0.79
     JSC
    0.79
     терито
    0.77
     N
    0.74
     A
    0.74
     Loma
    0.73
     V
    0.72
     territor
    0.71
    POSITIVE LOGITS
     diretor
    0.83
     criaturas
    0.82
     coeficiente
    0.79
    ус
    0.78
     conectar
    0.78
     confiar
    0.77
    عيه
    0.77
    पेक्षा
    0.76
    et
    0.75
     unbeliev
    0.75
    Activations Density 0.000%

    No Known Activations