© 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. 8242
    Prev
    Next
    INDEX
    Explanations

    text format specifications

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

    The neuron is triggered by numeric tokens that include a decimal point (i.e. floating-point numbers or measurements expressed with decimals).

    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
    İ
    0.78
     Në
    0.72
     evam
    0.69
     她
    0.68
    ıll
    0.67
    Ан
    0.67
    Ε
    0.65
    ܝܢ
    0.65
    ంథ
    0.65
     Samoa
    0.64
    POSITIVE LOGITS
    警戒
    0.72
    方向に
    0.65
     ору
    0.57
    тного
    0.55
     প্রাই
    0.55
    side
    0.54
    osity
    0.54
     கலங்கரை
    0.54
    ことにより
    0.54
     arcs
    0.54
    Activations Density 0.003%

    No Known Activations