© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    if else statements

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

    The neuron activates on numeric tokens that include decimal points (i.e. floating-point 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
    ต่อไป
    0.68
    Edited
    0.63
    edited
    0.62
    outline
    0.60
    </h5>
    0.60
    automatic
    0.59
    щего
    0.56
    ‬
    0.56
    Automatic
    0.55
    Actual
    0.55
    POSITIVE LOGITS
     Afro
    0.67
     UV
    0.65
     Sri
    0.64
    achal
    0.63
     UVA
    0.62
     urea
    0.61
     Ulu
    0.59
     Urea
    0.59
     Lynda
    0.58
     Bowling
    0.57
    Activations Density 0.000%

    No Known Activations