© 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. 41-GEMMASCOPE-2-RES-65K
    7. 15651
    Prev
    Next
    INDEX
    Explanations

    subject to change

    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
     lão
    0.55
     regardless
    0.54
     prepar
    0.53
     kullanarak
    0.53
     measuring
    0.52
    不管
    0.51
    不管是
    0.51
     論
    0.51
     travailleurs
    0.51
     sozinha
    0.50
    POSITIVE LOGITS
     tentative
    1.59
     tentatively
    1.38
     TBA
    1.38
     announced
    1.24
    announced
    1.20
     confirmed
    1.14
     determined
    1.12
     уточ
    1.12
    公布
    1.10
     Tent
    1.09
    Activations Density 0.138%

    No Known Activations