© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11622
    Prev
    Next
    INDEX
    Explanations

    free subscriptions, defense spending

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

    This neuron sharply activates on the very first substantive (non‐stop) word that begins a new segment or paragraph.

    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
    ب
    0.79
    دام
    0.77
    <0x80>
    0.73
    0
    0.71
     sized
    0.70
    да
    0.68
    esi
    0.68
    tei
    0.64
    नास
    0.63
    grove
    0.63
    POSITIVE LOGITS
     Эти
    1.09
     Fokker
    1.01
     Firefox
    0.98
     Deadpool
    0.95
     Э
    0.95
     Waffen
    0.92
     недель
    0.91
     المنت
    0.90
     Бы
    0.90
     problemen
    0.89
    Activations Density 0.000%

    No Known Activations