© 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. 9146
    Prev
    Next
    INDEX
    Explanations

    mind: confusion of mind: chill

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

    This neuron fires on numeric literals—especially decimal or fractional numbers—formatted as inline code or math.

    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
    core
    0.93
    BUF
    0.92
    ons
    0.88
    axis
    0.88
    s
    0.86
    surgeon
    0.85
    sock
    0.84
    Executor
    0.84
    waypoints
    0.84
    reel
    0.84
    POSITIVE LOGITS
     το
    0.83
     apprehend
    0.80
     pandemia
    0.77
     кня
    0.75
     е
    0.75
     следует
    0.74
     ях
    0.74
    因為
    0.73
    ेला
    0.73
     manca
    0.73
    Activations Density 0.000%

    No Known Activations