© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11807
    Prev
    Next
    INDEX
    Explanations

    function/variable names

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

    The neuron strongly activates on tokens that are floating‐point numbers (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
    au
    0.65
    ılar
    0.65
    $%
    0.65
     CommandCenter
    0.64
    ور
    0.63
    大家
    0.63
     又
    0.63
    &$
    0.62
    ಚ್ಚ
    0.62
    \}$,
    0.62
    POSITIVE LOGITS
     povos
    0.90
     alkaline
    0.88
    淈
    0.88
     जुड़ी
    0.83
    Ṭ
    0.82
     fertilizer
    0.82
     religione
    0.81
    ны
    0.79
     basalt
    0.79
     alkali
    0.77
    Activations Density 0.000%

    No Known Activations