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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15028
    Prev
    Next
    INDEX
    Explanations

    favorite

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     induced
    0.59
     Induced
    0.59
    induced
    0.48
     말미암
    0.48
    Induced
    0.48
     Redistributions
    0.47
    हून
    0.47
    贞
    0.47
    жны
    0.45
    تقرير
    0.45
    POSITIVE LOGITS
     favorite
    5.28
     favourite
    5.13
    favorite
    4.97
     Favorite
    4.84
    Favorite
    4.78
     Favourite
    4.53
     favorito
    4.50
     favorites
    4.44
    Favourite
    4.44
     favoritos
    4.38
    Activations Density 0.163%

    No Known Activations