© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7736
    Prev
    Next
    INDEX
    Explanations

    gambling and lottery input prompts

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

    The main thing this neuron does is detect numeric tokens with high-precision decimal values (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_31_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
    汚
    0.72
    ленного
    0.69
    stylesheets
    0.67
    ត្រូវការ
    0.66
    絶対に
    0.66
    全部
    0.65
    лянчук
    0.65
    дя
    0.65
    付ける
    0.64
    льбе
    0.64
    POSITIVE LOGITS
     นะ
    0.92
    𒐪
    0.90
     こ
    0.89
     Kerala
    0.89
     みたい
    0.88
     🤔
    0.86
     ます
    0.85
     🙏
    0.85
     🤗
    0.85
     😊
    0.84
    Activations Density 0.000%

    No Known Activations