© 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. 149879
    Prev
    Next
    INDEX
    Explanations

    multilingual text

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

    bypass filters, first instances

    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
     supported
    0.49
     we
    0.48
     achieve
    0.47
    ድ
    0.46
     beaches
    0.46
     Maraton
    0.46
    اکہ
    0.45
     commits
    0.45
     recreate
    0.44
     mitologia
    0.44
    POSITIVE LOGITS
     бюро
    0.45
     struggled
    0.45
     ಪ್ರಶ್
    0.45
     কারও
    0.43
     конце
    0.43
    難
    0.43
     вопросов
    0.42
     кап
    0.42
    觊
    0.42
     cuối
    0.42
    Activations Density 0.000%

    No Known Activations