© 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. 63456
    Prev
    Next
    INDEX
    Explanations

    positive evaluation of content and style

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

    plot and movie reviews

    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
     fraught
    0.47
     Scott
    0.46
     Scottsdale
    0.46
     preclude
    0.45
     esche
    0.44
     这些
    0.44
     Idaho
    0.43
     Scotts
    0.43
    馔
    0.42
     monastic
    0.42
    POSITIVE LOGITS
     deviated
    0.50
    фіка
    0.49
     keseluruhan
    0.49
    🖒
    0.49
     definitiv
    0.48
     definitely
    0.48
     আশ্চর্যজনক
    0.48
    😐
    0.47
     commendable
    0.47
    َہ
    0.47
    Activations Density 0.040%

    No Known Activations