© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5785
    Prev
    Next
    INDEX
    Explanations

    ongoing or persistent checks

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

    The neuron activates on numeric tokens—particularly digits, decimal numbers, and percentages.

    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
    bb
    0.88
     האח
    0.72
     ৃ
    0.69
    ну
    0.68
     Gerade
    0.67
     ощущение
    0.65
     그러니까
    0.64
    lVert
    0.64
    cono
    0.63
    begin
    0.62
    POSITIVE LOGITS
    ীন
    0.92
    萧
    0.87
     screenwriter
    0.86
     shirtless
    0.84
    साइड
    0.84
    罗斯
    0.84
     cheated
    0.82
     kleur
    0.81
     fär
    0.81
    絭
    0.79
    Activations Density 0.001%

    No Known Activations