© 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. 7308
    Prev
    Next
    INDEX
    Explanations

    consequences and following actions

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

    The main thing this neuron does is detect floating‐point numeric tokens (numbers containing a decimal point).

    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
     Thrive
    0.66
    _);
    0.65
    Require
    0.63
     Uniwers
    0.62
    У
    0.62
    Easing
    0.61
    Via
    0.60
     Fiona
    0.60
     Cumulative
    0.60
    OUTH
    0.60
    POSITIVE LOGITS
    景区
    0.66
    夲
    0.65
    例えば
    0.62
    ன்களை
    0.62
     örnek
    0.61
    ліся
    0.61
    
    0.61
    侸
    0.60
    exemple
    0.59
     hotspots
    0.59
    Activations Density 0.000%

    No Known Activations