© 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. 108784
    Prev
    Next
    INDEX
    Explanations

    film lies

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

    communication, yourself, needs

    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
    ̀ng
    0.52
    銷售
    0.47
    अरविंद
    0.46
     טור
    0.46
    ți
    0.45
    ğini
    0.44
    َ
    0.43
     Евгений
    0.43
     કુલ
    0.42
     الجمهور
    0.42
    POSITIVE LOGITS
     }^{[
    0.48
     cinema
    0.47
     Cinema
    0.45
     ecosystem
    0.44
     myopia
    0.44
     environment
    0.44
     Wolverhampton
    0.44
    ρο
    0.44
     Microscopy
    0.44
     Diary
    0.43
    Activations Density 0.006%

    No Known Activations