© 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. 12086
    Prev
    Next
    INDEX
    Explanations

    in variable assignment

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

    The neuron detects decimal numbers (floating-point numerical values) embedded in the text.

    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
     비롯
    0.92
    ból
    0.91
    ᶤ
    0.85
     Nä
    0.83
     씨
    0.79
    ٩
    0.79
     individuais
    0.78
    实话
    0.77
    rán
    0.77
    ből
    0.77
    POSITIVE LOGITS
    $
    0.71
     rapt
    0.70
    "
    0.70
    ?).
    0.68
                            
    0.68
     myth
    0.67
    getPort
    0.67
     hic
    0.66
     rab
    0.66
     hepat
    0.65
    Activations Density 0.000%

    No Known Activations