© 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. 31-GEMMASCOPE-2-RES-16K
    7. 609
    Prev
    Next
    INDEX
    Explanations

    list separators

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

    The neuron detects numerical tokens (e.g. years, quantities, large 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_31_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
    த்தைத்
    0.46
     etcétera
    0.46
    中有
    0.44
    屢
    0.44
    লীগের
    0.44
    ();//
    0.43
     véritables
    0.43
    ()">
    0.42
     ನೆಲ
    0.42
     உலகம்
    0.42
    POSITIVE LOGITS
    ،
    1.90
    ,
    1.80
    ，
    1.69
    ၊
    1.58
     ,
    1.51
     ،
    1.50
    ፣
    1.50
    ,,
    1.44
    ,\
    1.43
    .,
    1.36
    Activations Density 1.013%

    No Known Activations