© 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. 8185
    Prev
    Next
    INDEX
    Explanations

    starting phrase

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

    The neuron detects numeric tokens (especially multi‐digit numbers and decimals).

    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
    一個
    0.91
    你有
    0.89
    你
    0.87
    你能
    0.84
     Your
    0.84
    Your
    0.84
     তুমি
    0.83
    你要
    0.83
     Yourself
    0.83
     Didn
    0.82
    POSITIVE LOGITS
    ;
    0.95
     or
    0.83
     selectors
    0.81
    ;,
    0.72
     operations
    0.69
    ;"
    0.68
    .;
    0.67
    ;\
    0.67
     mower
    0.67
     section
    0.66
    Activations Density 0.030%

    No Known Activations