© 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. 4427
    Prev
    Next
    INDEX
    Explanations

    folder names or file paths

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

    The neuron strongly activates on tokens representing floating‐point (decimal) 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
     de
    0.76
    y
    0.73
    할
    0.71
    ObjectMapper
    0.66
     April
    0.66
     dimiliki
    0.66
    k
    0.66
     économiques
    0.66
    ي
    0.66
    April
    0.65
    POSITIVE LOGITS
     Defts
    0.90
     aead
    0.80
     Paula
    0.80
    ਿਕ
    0.79
     aloft
    0.78
     promulgated
    0.77
     Matth
    0.77
     supplemented
    0.76
     instituted
    0.76
    licos
    0.76
    Activations Density 0.000%

    No Known Activations