© 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. 14798
    Prev
    Next
    INDEX
    Explanations

    why or asking why

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

    The neuron consistently lights up on numeric tokens representing decimal-point measurements (floating-point numbers).

    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
    این
    0.80
    この
    0.79
    私も
    0.72
    astanza
    0.71
    但
    0.71
    آ
    0.70
    ときの
    0.69
    妾
    0.69
    アー
    0.68
     معظم
    0.68
    POSITIVE LOGITS
    '?
    0.85
     recreating
    0.79
     estuary
    0.79
     нормы
    0.78
     fuelled
    0.75
     retrograde
    0.73
     fertilisers
    0.73
    plotting
    0.73
     stabilise
    0.73
    ৃ
    0.73
    Activations Density 0.000%

    No Known Activations