© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11454
    Prev
    Next
    INDEX
    Explanations

    programming imports

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

    The neuron strongly activates on numeric tokens (including version numbers, digits, and digit-containing identifiers).

    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
     _,
    0.67
    Typed
    0.62
     Typed
    0.57
     String
    0.57
     camisetas
    0.57
    クエスト
    0.56
     deviated
    0.55
    *;
    0.52
     القي
    0.52
     fudai
    0.51
    POSITIVE LOGITS
    mydb
    0.55
    myButtons
    0.54
     дос
    0.53
     मारने
    0.53
    present
    0.52
     способен
    0.52
    omyces
    0.51
    $&$-
    0.51
    almost
    0.50
    rentice
    0.50
    Activations Density 0.006%

    No Known Activations