© 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. 109482
    Prev
    Next
    INDEX
    Explanations

    RDF and XML schema prefixes

    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
     પટેલ
    0.42
     demise
    0.42
     cardiomyocyte
    0.42
     inducible
    0.40
     speciality
    0.40
     impon
    0.40
     pequena
    0.39
    „
    0.39
     Besonders
    0.39
     approximate
    0.39
    POSITIVE LOGITS
    ├──
    0.44
    ří
    0.43
    rés
    0.41
     Архів
    0.41
     첨
    0.40
     Branding
    0.40
     テ
    0.40
     Тер
    0.40
    ités
    0.39
    ään
    0.39
    Activations Density 0.004%

    No Known Activations