© 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. 11546
    Prev
    Next
    INDEX
    Explanations

    designed to be capable

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

    The neuron primarily detects numeric tokens, especially floating-point numbers and decimal 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
     случи
    0.78
    就行
    0.74
    只需要
    0.72
    是你
    0.71
     será
    0.70
    ใหม่
    0.70
     baru
    0.68
    幸
    0.67
     itulah
    0.67
     ruining
    0.66
    POSITIVE LOGITS
     resourceful
    0.79
     fréquemment
    0.77
     frequentemente
    0.77
     često
    0.75
     인식
    0.75
     lecteur
    0.74
     다양한
    0.73
     často
    0.73
     tanıml
    0.72
     perceptual
    0.72
    Activations Density 0.087%

    No Known Activations