© 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. 6856
    Prev
    Next
    INDEX
    Explanations

    plays, time, Tokyo

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

    The neuron primarily detects floating-point numeric tokens (numbers containing a decimal point).

    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
    َات
    0.72
     nya
    0.70
     प्रस्तावित
    0.70
     Zeitpunkt
    0.69
    ﺻ
    0.68
     用
    0.68
     nhỉ
    0.68
     Suddenly
    0.67
    ونات
    0.67
    лежа
    0.66
    POSITIVE LOGITS
    Codigo
    0.82
    ระหว่าง
    0.80
    Agu
    0.77
    קו
    0.76
    ป
    0.73
    तर
    0.73
    ก
    0.73
    王国
    0.71
    ربي
    0.70
    ➀
    0.70
    Activations Density 0.000%

    No Known Activations