© 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. 43158
    Prev
    Next
    INDEX
    Explanations

    titles, narrator, easily, credited

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

    foreign language words and concepts

    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
    am
    0.52
    ed
    0.48
     असलेल्या
    0.45
     cửa
    0.44
     injecting
    0.44
    neho
    0.43
    USTR
    0.42
    夶
    0.42
    iy
    0.42
     अवगत
    0.42
    POSITIVE LOGITS
     результата
    0.47
     Engels
    0.43
     SIST
    0.43
     laranja
    0.43
     perinatal
    0.43
    烂
    0.42
     projet
    0.42
     কন
    0.42
     foc
    0.42
     gameState
    0.42
    Activations Density 0.000%

    No Known Activations