© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52777
    Prev
    Next
    INDEX
    Explanations

    new

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

    contact information numbers and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ँ
    0.56
     राउत
    0.50
     일반
    0.49
     text
    0.46
    práv
    0.46
     observer
    0.45
    खिक
    0.45
     $\
    0.44
     outset
    0.44
    ிலை
    0.44
    POSITIVE LOGITS
     nuovi
    0.57
     الجديدة
    0.55
    新的
    0.53
    バター
    0.52
     nuove
    0.51
    নতুন
    0.50
     নতুন
    0.49
     nuovo
    0.49
    州的
    0.49
     ನ್ಯಾಯ
    0.49
    Activations Density 0.000%

    No Known Activations