© 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. 7618
    Prev
    Next
    INDEX
    Explanations

    code and programming terms

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

    The neuron detects and strongly activates on floating-point numeric 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
     mesmos
    0.83
     উহা
    0.74
     mesmas
    0.74
    λαμβ
    0.73
    ,
    0.72
     Vergangenheit
    0.71
     mismos
    0.66
     extrapolated
    0.66
     stessi
    0.65
     mêmes
    0.63
    POSITIVE LOGITS
    sunset
    0.79
     Carpath
    0.79
    ic
    0.78
    son
    0.77
    厦门
    0.77
    ጄ
    0.77
    ेश्वर
    0.75
    ドラゴン
    0.73
     chiếc
    0.73
     caramel
    0.73
    Activations Density 0.000%

    No Known Activations