© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9813
    Prev
    Next
    INDEX
    Explanations

    questions about attending, extra, device, email

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

    The neuron is specialized to pick out numeric tokens that include decimal points (i.e. 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
    ‌ی
    0.86
    cfg
    0.81
    ک
    0.80
     behavioral
    0.76
    kp
    0.75
    p
    0.73
    ای
    0.73
    c
    0.72
     connectors
    0.71
    czny
    0.71
    POSITIVE LOGITS
     sür
    0.83
     nemá
    0.80
     ngành
    0.78
     nữ
    0.77
    isesti
    0.77
     sambil
    0.77
     thử
    0.75
     após
    0.73
     má
    0.73
     eosin
    0.73
    Activations Density 0.000%

    No Known Activations