© 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. 6760
    Prev
    Next
    INDEX
    Explanations

    function achieved, Early, intermittent, somewhat

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

    The neuron is detecting floating‐point number tokens (i.e. numeric values with decimal points).

    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
    od
    0.98
    ok
    0.93
    ud
    0.86
    ia
    0.85
    Modal
    0.85
    forc
    0.83
    ue
    0.83
    5
    0.82
    0
    0.81
    ils
    0.80
    POSITIVE LOGITS
     explorar
    0.91
     고
    0.87
     피
    0.84
     liquido
    0.84
     bivariate
    0.83
     グ
    0.83
     ಹೆಚ್ಚಿನ
    0.83
     수상
    0.82
     변화
    0.81
     ಕೆಲವು
    0.80
    Activations Density 0.000%

    No Known Activations