© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4898
    Prev
    Next
    INDEX
    Explanations

    building world senses

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

    The neuron activates on floating‐point numbers (numerical values with decimal points).

    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
    )。
    0.96
    camp
    0.76
     mettant
    0.75
    .${
    0.73
    /).
    0.71
     elaboración
    0.70
     Armando
    0.70
     échantillons
    0.70
    َم
    0.69
    .{
    0.66
    POSITIVE LOGITS
    к
    0.88
     শাল
    0.82
    л
    0.81
     Wellness
    0.80
    вы
    0.78
    ಲಿ
    0.77
    ל
    0.77
     Её
    0.75
    ı
    0.73
    ח
    0.72
    Activations Density 0.001%

    No Known Activations