© 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. 41185
    Prev
    Next
    INDEX
    Explanations

    year old, flash mob, Greek music, sheep, forensic evaluation, viral quiz

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

    potential performance

    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
     Force
    0.45
     ﺍ
    0.43
    ISTS
    0.42
    INESS
    0.42
     Administração
    0.40
     Preface
    0.39
     in
    0.39
    ﺩ
    0.38
     official
    0.38
     “[
    0.38
    POSITIVE LOGITS
    で行
    0.48
    बी
    0.47
    шча
    0.47
    だけでなく
    0.46
    केजी
    0.45
    विधा
    0.45
    sprecher
    0.45
     재미
    0.44
    毌
    0.44
    𝕆
    0.43
    Activations Density 0.000%

    No Known Activations