© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6762
    Prev
    Next
    INDEX
    Explanations

    attention mechanism, concept, phenomenon

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

    The neuron fires on numeric tokens—especially decimal‐style or other raw numerical values—highlighting when the text contains standalone numbers.

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ==>
    0.59
     ";//
    0.50
     ...");
    0.50
     <=>
    0.50
     (*)
    0.48
     √(
    0.46
    のス
    0.46
     //</
    0.46
     :");
    0.45
     (|
    0.45
    POSITIVE LOGITS
    lication
    0.55
    ATHER
    0.54
    イツ
    0.52
    ains
    0.50
    gems
    0.50
    फिया
    0.50
     Maize
    0.50
    adder
    0.49
    athom
    0.49
     അയാൾ
    0.47
    Activations Density 2.134%

    No Known Activations