© 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. 9326
    Prev
    Next
    INDEX
    Explanations

    LinkedIn Profile

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

    This neuron primarily fires on slash (“/”) characters in URLs and file‐path strings.

    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
     Skies
    0.79
    t
    0.76
    d
    0.75
    ز
    0.71
    的小
    0.70
    引领
    0.67
    h
    0.66
     rivers
    0.66
     skies
    0.65
    g
    0.65
    POSITIVE LOGITS
     carrito
    0.96
     связь
    0.93
     आइए
    0.92
     veinte
    0.91
     ustedes
    0.90
     impresora
    0.90
     bienestar
    0.86
    planner
    0.86
     тільки
    0.85
     ejecutivo
    0.84
    Activations Density 0.000%

    No Known Activations