© 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. 13277
    Prev
    Next
    INDEX
    Explanations

    sidereal, constructivism, Mandate, vicuña, specifically

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

    This neuron is highly sensitive to comma punctuation marks.

    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
     elucid
    1.00
     transgress
    0.97
     대부분
    0.90
    슌
    0.86
     gases
    0.85
     inú
    0.85
     식
    0.85
     rumin
    0.85
     erythemat
    0.84
     अधिकांश
    0.84
    POSITIVE LOGITS
    song
    0.96
    tin
    0.93
    en
    0.91
    tone
    0.91
    srt
    0.88
    two
    0.85
    tam
    0.85
    t
    0.85
    sdk
    0.84
    tf
    0.84
    Activations Density 0.001%

    No Known Activations