© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199379
    Prev
    Next
    INDEX
    Explanations

    operated by Mercedes cars

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

    regions of

    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
     स्वरूप
    0.50
    这
    0.50
    도
    0.50
     surges
    0.49
    偐
    0.49
    Ր
    0.47
    喿
    0.46
    珏
    0.46
    斯
    0.45
    장
    0.45
    POSITIVE LOGITS
     ಕೊಟ್ಟ
    0.45
     Hellen
    0.44
     обратно
    0.44
    kitty
    0.43
     authorise
    0.42
     kaufen
    0.42
     Schengen
    0.41
     Cath
    0.41
    iol
    0.41
    WRITE
    0.41
    Activations Density 0.001%

    No Known Activations