© 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. 12490
    Prev
    Next
    INDEX
    Explanations

    foreign or non-English words

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

    The neuron is activated by floating‐point numeric tokens (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
    F
    0.80
    値
    0.74
    i
    0.73
    E
    0.70
    N
    0.70
    P
    0.68
    u
    0.67
    L
    0.67
    T
    0.66
    ち
    0.66
    POSITIVE LOGITS
     från
    0.75
    সব
    0.71
     இந்தக்
    0.69
     този
    0.67
     образом
    0.66
     tämä
    0.66
     وهذه
    0.66
     машиналары
    0.64
     herkes
    0.64
    ού
    0.63
    Activations Density 0.001%

    No Known Activations