© 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. 8975
    Prev
    Next
    INDEX
    Explanations

    fabrications stating incorrect information

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

    This neuron fires on the very first non‐stopword “content” token at the start of each new sentence or segment.

    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
    lacian
    0.75
    ی
    0.73
    //!
    0.71
    !)
    0.70
    Bounding
    0.70
    没想到
    0.68
    s
    0.68
     midfield
    0.68
    핫
    0.68
    لی
    0.67
    POSITIVE LOGITS
     Иң
    0.87
     ทั้ง
    0.86
     Như
    0.86
     Rä
    0.83
     ตาม
    0.83
     көрс
    0.83
     құ
    0.82
     Konstant
    0.82
     Такой
    0.82
     לפי
    0.80
    Activations Density 0.000%

    No Known Activations