© 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. 4100
    Prev
    Next
    INDEX
    Explanations

    case-insensitive comparisons/conversions

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

    The neuron fires on named‐entity tokens—proper nouns and numerical or alphanumeric identifiers.

    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
    numbers
    0.75
     headwinds
    0.75
     Вы
    0.75
    number
    0.73
    
    0.71
     看
    0.71
    nG
    0.70
     zeroes
    0.70
    8
    0.70
    ২৯
    0.68
    POSITIVE LOGITS
     autorisé
    0.79
     iliş
    0.78
     destiné
    0.77
     porte
    0.77
     saint
    0.75
     déterminer
    0.75
     ouvert
    0.74
    لقة
    0.73
     ellen
    0.73
    を示
    0.73
    Activations Density 0.001%

    No Known Activations