© 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. 10119
    Prev
    Next
    INDEX
    Explanations

    New Delhi

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

    The neuron activates on numerical 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
    Z
    0.75
    Ihr
    0.74
     absor
    0.73
    場合がございます
    0.72
     นะ
    0.70
     dirige
    0.70
    おすすめ
    0.69
    ご利用
    0.69
    2
    0.68
    Community
    0.67
    POSITIVE LOGITS
    ⁃
    0.86
     Spurs
    0.83
     местах
    0.82
    цкі
    0.81
    ی
    0.81
     Senado
    0.80
    coconut
    0.79
    ්
    0.79
    욥
    0.79
     tume
    0.78
    Activations Density 0.000%

    No Known Activations