© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3219
    Prev
    Next
    INDEX
    Explanations

    com.example

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

    This neuron detects URL components (e.g. the “com”, dots, and slashes) indicative of web addresses.

    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
     тях
    0.58
    Ї
    0.58
     їх
    0.55
    didn
    0.55
     cursory
    0.55
    Від
    0.55
    股权
    0.54
    Blessed
    0.54
    ји
    0.53
    ၵ
    0.53
    POSITIVE LOGITS
     Moderate
    0.54
     voorbeeld
    0.54
     example
    0.53
     เซ
    0.51
     EXAMPLE
    0.50
    isca
    0.50
     exemplo
    0.50
    Maquina
    0.50
     ejemplo
    0.49
     ニ
    0.49
    Activations Density 0.014%

    No Known Activations