© 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. 10982
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical terms

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

    The neuron specifically detects numeric tokens containing decimal points (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
     ragged
    0.84
     succumb
    0.84
     halt
    0.83
    owskiego
    0.81
     hopped
    0.81
    秶
    0.80
     weapons
    0.80
     succumbed
    0.80
     rus
    0.79
    া
    0.79
    POSITIVE LOGITS
    クラブ
    0.86
    ابی
    0.77
    ક્સ
    0.75
     Trouvez
    0.74
     également
    0.72
     När
    0.71
    Create
    0.71
    椹
    0.70
    iranje
    0.70
    织
    0.70
    Activations Density 0.000%

    No Known Activations