© 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. 14057
    Prev
    Next
    INDEX
    Explanations

    immediate reward

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

    The neuron fires on tokens representing precise floating‐point numbers (decimal measurements).

    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
    antics
    0.79
    в
    0.77
    olle
    0.77
    ل
    0.71
    john
    0.70
    jg
    0.70
    irr
    0.70
    ants
    0.69
    ב
    0.69
    ע
    0.69
    POSITIVE LOGITS
    ﻘ
    0.95
     итоге
    0.93
     quiera
    0.91
     quería
    0.87
    ~!
    0.85
     estup
    0.85
     accruing
    0.84
     станет
    0.84
     너
    0.83
     accueille
    0.82
    Activations Density 0.001%

    No Known Activations