© 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. 191196
    Prev
    Next
    INDEX
    Explanations

    multiple languages

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

    you are or haven

    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
    Negative Logits
    PROOF
    0.51
    başı
    0.48
    Za
    0.46
    purchase
    0.46
    Upgradeable
    0.46
    র
    0.45
     Invited
    0.45
    Rest
    0.45
    r
    0.45
    previously
    0.44
    POSITIVE LOGITS
    îtes
    0.45
     मिर्च
    0.45
    ossed
    0.43
    姪
    0.43
     ہون
    0.43
     तसेच
    0.43
     σχετικά
    0.42
     люди
    0.42
     쓰고
    0.42
     단순히
    0.41
    Activations Density 0.000%

    No Known Activations