© 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. 9370
    Prev
    Next
    INDEX
    Explanations

    reached

    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
    畬
    0.40
     περισσότε
    0.39
     powerAll
    0.38
     automático
    0.38
     kinda
    0.37
    وروب
    0.36
     ಕೇಂದ್ರ
    0.36
     próxim
    0.36
    तावनी
    0.36
     tất
    0.35
    POSITIVE LOGITS
    perms
    0.37
     n
    0.37
    perm
    0.36
    ro
    0.36
    krit
    0.35
    verbal
    0.35
    java
    0.35
    ysel
    0.34
                
    0.34
    ѝ
    0.34
    Activations Density 0.008%

    No Known Activations