© 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. 12525
    Prev
    Next
    INDEX
    Explanations

    processing sequential

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

    The neuron fires strongly on message‐header markers—that is, lines beginning with a subject or heading prefix like “Re:”

    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
    া
    0.93
    ی
    0.93
    ن
    0.84
    م
    0.78
    л
    0.77
    ва
    0.75
    <0xB7>
    0.73
    𝓱
    0.73
    сі
    0.71
    ці
    0.71
    POSITIVE LOGITS
     yine
    0.89
    ਆਂ
    0.86
    alık
    0.84
    kring
    0.80
     digelar
    0.79
    kle
    0.79
    schnitt
    0.77
    mesinin
    0.77
    umal
    0.75
    গন্ধ
    0.75
    Activations Density 0.001%

    No Known Activations