© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    AI, greatest, Ball, something, goat, Pepper

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

    The neuron specializes in spotting numeric measurements or large numerical values (e.g., decimal or multi‐digit numbers).

    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
    nus
    0.96
    amai
    0.94
    nv
    0.94
    nol
    0.92
    nę
    0.91
    sa
    0.89
    tim
    0.89
    𝐭
    0.89
    urada
    0.86
    nr
    0.86
    POSITIVE LOGITS
     reinforcement
    0.79
     nurt
    0.74
     Prisoner
    0.72
     Jahrze
    0.71
     knack
    0.70
     ১৯৯
    0.70
     flurry
    0.70
     labors
    0.70
     nutrient
    0.68
     furnishing
    0.68
    Activations Density 0.000%

    No Known Activations