© 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. 7813
    Prev
    Next
    INDEX
    Explanations

    Country or software development context

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

    This neuron selectively activates on numeric tokens written with 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_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
    н
    0.83
    nä
    0.81
    𝐭
    0.80
    нци
    0.78
    egrave
    0.74
    eux
    0.73
    oeuvre
    0.73
     êtres
    0.73
    т
    0.72
    𝐞
    0.71
    POSITIVE LOGITS
    .
    0.90
    ին
    0.82
     fainting
    0.82
     rattan
    0.79
     barrage
    0.78
     Loại
    0.77
    ación
    0.77
    निम्नलिखित
    0.77
     unkind
    0.76
     velvet
    0.76
    Activations Density 0.000%

    No Known Activations