© 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. 13255
    Prev
    Next
    INDEX
    Explanations

    shemale, startup idea, Humans, Gemini, price, db

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

    The neuron mainly detects numeric tokens with decimal (floating-point) 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
    要做
    0.78
    分辨率
    0.71
    奇异
    0.71
     encima
    0.70
    朮
    0.70
    thr
    0.70
     supersymmetry
    0.70
    ⇔
    0.69
    وما
    0.68
     复
    0.68
    POSITIVE LOGITS
     ভিত্তিতে
    0.70
    사의
    0.70
     pomocí
    0.69
    िया
    0.68
    ן
    0.68
     provare
    0.68
    ளைஞ
    0.67
     nonostante
    0.67
     হ্যান
    0.66
     ******
    0.66
    Activations Density 0.000%

    No Known Activations