© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9800
    Prev
    Next
    INDEX
    Explanations

    explanationscripts, and communication

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

    The neuron is sensitive to technical instructions describing precise foot‐placement stance geometry (e.g. “toe-to-head” or “toe-to-instep” positioning).

    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
     in
    0.74
     new
    0.72
    ;
    0.70
    in
    0.68
     în
    0.67
     without
    0.67
     새
    0.67
     with
    0.66
    g
    0.65
     eliminates
    0.65
    POSITIVE LOGITS
     혹은
    0.98
    もしくは
    0.98
    หรือ
    0.98
     ataupun
    0.95
     yoki
    0.94
    或者
    0.88
    或者是
    0.88
    或是
    0.86
    または
    0.84
     లేదా
    0.84
    Activations Density 0.294%

    No Known Activations