© 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. 7653
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

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

    The neuron fires on numeric tokens with decimal points (e.g., timestamps or reference values).

    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
     OSHA
    0.70
    sville
    0.61
     mathbf
    0.60
     aborted
    0.60
     暗
    0.58
     Kn
    0.58
     Spotted
    0.57
    不大
    0.57
    mary
    0.56
     Tire
    0.56
    POSITIVE LOGITS
     преодо
    0.90
    콧
    0.84
    кал
    0.83
    SEP
    0.80
    CAB
    0.79
    కుల
    0.79
    ្នក
    0.78
    NEE
    0.78
    instrument
    0.77
    ្ម
    0.77
    Activations Density 0.000%

    No Known Activations