© 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. 43245
    Prev
    Next
    INDEX
    Explanations

    forthcoming MG series

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

    compilation video

    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
     ሆ
    0.45
    ्रा
    0.44
    getSaveLocation
    0.43
    ucumber
    0.43
    లతో
    0.43
    ণ
    0.42
    verticalLayout
    0.42
    ственного
    0.41
    OffsetY
    0.41
    subsec
    0.40
    POSITIVE LOGITS
     comunic
    0.49
     begrenzt
    0.49
    <!
    0.48
    Iy
    0.48
     sami
    0.47
     criticize
    0.47
    ğa
    0.46
     fortuna
    0.45
     sired
    0.45
     rhy
    0.44
    Activations Density 0.000%

    No Known Activations