© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5962
    Prev
    Next
    INDEX
    Explanations

    transition or a sequence

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

    The neuron is strongly activated by numeric tokens, especially floating‐point numbers (decimal 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
     respective
    0.79
    ર
    0.73
    ้า
    0.68
    posX
    0.68
     SECOND
    0.66
    و
    0.66
     révolution
    0.65
    不動
    0.65
    лле
    0.64
    ->
    0.64
    POSITIVE LOGITS
     ofrecemos
    0.88
     klar
    0.87
     contamos
    0.87
    ﻢ
    0.87
    datast
    0.85
    Ml
    0.84
    owanie
    0.83
     chiaro
    0.83
     claras
    0.83
    bildung
    0.82
    Activations Density 0.000%

    No Known Activations