© 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. 14505
    Prev
    Next
    INDEX
    Explanations

    stripes, theory, fib, less, key, Coins

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

    The neuron fires on non‐text formatting or metadata markers—especially bracket characters and unusual Unicode punctuation used for dates or inline annotations.

    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
     ديسمبر
    0.85
     เส้น
    0.82
     וא
    0.82
    <0x80>
    0.79
     או
    0.78
    軖
    0.77
     וי
    0.77
     Cultures
    0.77
     黃
    0.76
     Salaries
    0.75
    POSITIVE LOGITS
    ak
    0.79
    ţi
    0.76
    砕
    0.74
    たく
    0.73
    ْت
    0.71
    bered
    0.71
    bracht
    0.70
    ți
    0.70
    steacher
    0.70
    teros
    0.69
    Activations Density 0.000%

    No Known Activations