© 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. 15528
    Prev
    Next
    INDEX
    Explanations

    NOTE

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

    This neuron fires strongly on single-letter list or section markers (like “a.”, “b)”, “c.”, “f.”) used to label outline items.

    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
    镭
    0.70
     تنظیم
    0.70
     კარ
    0.67
     difíc
    0.66
     ร
    0.65
     conocimiento
    0.65
     sổ
    0.65
     جميلة
    0.64
     čp
    0.64
     condolences
    0.64
    POSITIVE LOGITS
    :
    0.66
     also
    0.62
    Nicht
    0.59
     consequence
    0.57
     –
    0.57
     Oracle
    0.55
    这也
    0.55
     arbitrary
    0.55
     أيضاً
    0.55
     standstill
    0.55
    Activations Density 0.046%

    No Known Activations