© 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. 14055
    Prev
    Next
    INDEX
    Explanations

    SQL queries

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

    This neuron primarily detects decimal‐point numbers (floating-point numeric tokens).

    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
    нім
    0.80
     网
    0.78
    нього
    0.77
     cancelled
    0.75
    ée
    0.73
    ніх
    0.73
    원
    0.71
     &/
    0.70
    не
    0.70
    셩
    0.68
    POSITIVE LOGITS
     estando
    0.89
    eleaf
    0.86
     minutos
    0.83
    schule
    0.83
     refor
    0.82
     листь
    0.82
     folhas
    0.82
     Sava
    0.80
     antigos
    0.79
     jangka
    0.79
    Activations Density 0.001%

    No Known Activations