© 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. 3491
    Prev
    Next
    INDEX
    Explanations

    impact of

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

    This neuron detects numeric tokens—especially long multi-digit or floating-point numbers—in the text.

    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
     kuidas
    0.78
    ুর
    0.71
    ែល
    0.70
    нняя
    0.70
    Ղ
    0.70
     कह
    0.68
    んと
    0.67
    sley
    0.66
    ्स
    0.66
    จาก
    0.66
    POSITIVE LOGITS
     bekam
    0.63
     aumento
    0.62
     longues
    0.62
     rendimiento
    0.61
    0.61
     وعلى
    0.59
    的影响
    0.59
     śnie
    0.59
    行驶
    0.58
     $+\
    0.58
    Activations Density 0.008%

    No Known Activations