© 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. 5385
    Prev
    Next
    INDEX
    Explanations

    categories or structured items

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

    The main thing this neuron does is detect numeric tokens (sequences of digits) in the text.

    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
     ذلك
    0.70
     dentre
    0.70
     essas
    0.68
     لهذه
    0.67
    ڳ
    0.67
     そこ
    0.66
     o
    0.66
     ceea
    0.66
     ।
    0.63
     forsk
    0.63
    POSITIVE LOGITS
    علي
    0.54
    ર્મા
    0.54
    unit
    0.53
    ただし
    0.52
    िसो
    0.52
    อื่นๆ
    0.51
    силання
    0.50
    込ま
    0.50
    ちなみに
    0.50
     другими
    0.50
    Activations Density 0.214%

    No Known Activations