© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3189
    Prev
    Next
    INDEX
    Explanations

    seeing this?!

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

    This neuron picks out numeric tokens—especially multi-digit or 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
     STEELS
    1.11
     homomorphisms
    0.95
     казіно
    0.91
    掷
    0.88
     буквально
    0.87
    异步
    0.86
     automorphisms
    0.84
    ナソニック
    0.84
     TypeScript
    0.83
     Shimano
    0.82
    POSITIVE LOGITS
    تور
    0.73
    s
    0.72
    ت
    0.71
    tie
    0.70
    తం
    0.69
    tion
    0.68
    nehmer
    0.67
    گە
    0.65
    k
    0.65
     coating
    0.64
    Activations Density 0.000%

    No Known Activations