© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3299
    Prev
    Next
    INDEX
    Explanations

    pakistani, wakefulness

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

    The neuron strongly activates on specific proper names or unique named entities.

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ்களின்
    0.73
    мі
    0.70
    কারণ
    0.70
    ті
    0.68
    تر
    0.67
    ล
    0.67
    굽
    0.67
    са
    0.64
    ̆
    0.64
    ন্দ্র
    0.63
    POSITIVE LOGITS
    kinen
    1.02
    ின்றன
    0.88
    nown
    0.87
    eeper
    0.86
    ின்றனர்
    0.83
    ின்றது
    0.79
    ிறார்கள்
    0.79
    itekt
    0.76
    owski
    0.75
    jaer
    0.75
    Activations Density 0.867%

    No Known Activations