© 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. 7153
    Prev
    Next
    INDEX
    Explanations

    types and preferences

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

    The neuron 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
    ка
    0.79
     една
    0.70
     б
    0.70
    ла
    0.68
    та
    0.68
     weir
    0.67
     oxen
    0.66
     bronze
    0.66
     అందుకు
    0.65
     emergency
    0.65
    POSITIVE LOGITS
    г
    0.84
    sch
    0.82
     intentos
    0.81
    ,)
    0.80
    スクリーン
    0.78
    preds
    0.78
    فظ
    0.77
    蛋白
    0.77
     Kräfte
    0.77
    呑
    0.77
    Activations Density 0.004%

    No Known Activations