© 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. 5332
    Prev
    Next
    INDEX
    Explanations

    bullet points

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

    The neuron is detecting numeric values expressed 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
    y
    0.98
    й
    0.95
    с
    0.86
    ي
    0.84
    да
    0.82
    tı
    0.82
    a
    0.81
    s
    0.81
    h
    0.79
    at
    0.79
    POSITIVE LOGITS
     desempenho
    0.89
     oficialmente
    0.79
     solicitudes
    0.78
    ,—
    0.77
     mennesker
    0.77
    ধ্যার
    0.76
     ludzi
    0.76
     dign
    0.75
    绚
    0.75
     cerve
    0.75
    Activations Density 0.001%

    No Known Activations