© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80089
    Prev
    Next
    INDEX
    Explanations

    Players, folks, content, schedule, cracking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     yardımcı
    0.48
     pomoći
    0.46
    ോട്ട്
    0.46
     öğretmen
    0.46
    Infrastructure
    0.45
    Fridge
    0.44
     मुफ्त
    0.44
     zestaw
    0.44
    ༞
    0.43
    Installation
    0.43
    POSITIVE LOGITS
     ಕೆಲವು
    0.50
     somewhat
    0.48
     glassy
    0.44
     Quelques
    0.43
     статей
    0.43
     каждую
    0.42
    рий
    0.41
    plaintext
    0.41
    ಃ
    0.41
     Yves
    0.40
    Activations Density 0.007%

    No Known Activations