© 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. 3494
    Prev
    Next
    INDEX
    Explanations

    not followed by assertion

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

    The neuron is a strong detector for the negation “not.”

    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
     aucune
    0.88
     unfl
    0.86
     necessitates
    0.78
     enforce
    0.75
    り
    0.73
     aucun
    0.72
     gents
    0.72
    Y
    0.72
     onslaught
    0.71
     WITH
    0.69
    POSITIVE LOGITS
    turno
    0.96
    ᵇ
    0.91
    عکس
    0.89
    cake
    0.88
     ఒక
    0.87
    देव
    0.86
    वेलकम
    0.86
    безпе
    0.85
    ört
    0.84
    tingham
    0.84
    Activations Density 0.112%

    No Known Activations