© 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. 13131
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron detects floating‐point numerical tokens (numbers with decimal points).

    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
     свої
    0.91
     cercanos
    0.88
     entrev
    0.81
     cercano
    0.77
     acced
    0.76
     cercana
    0.76
    ꜱ
    0.75
    𝙨
    0.73
     delitos
    0.73
     bütün
    0.73
    POSITIVE LOGITS
    ↵
    0.78
    uiden
    0.71
     niej
    0.70
    za
    0.66
     shared
    0.64
     driver
    0.63
     consensus
    0.63
     要
    0.63
     packageName
    0.63
     الأساس
    0.63
    Activations Density 0.001%

    No Known Activations