© 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-65K
    7. 31565
    Prev
    Next
    INDEX
    Explanations

    ` or `or`

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Developing
    0.44
    титься
    0.42
    specifiedByURL
    0.41
    东南
    0.41
    ыл
    0.40
    নীতিক
    0.39
     юго
    0.39
    振兴
    0.39
    
    0.39
    市场
    0.39
    POSITIVE LOGITS
    et
    0.48
     Sw
    0.47
     Can
    0.46
    hir
    0.45
    ↵
    0.45
     Gave
    0.44
     Or
    0.44
    at
    0.43
    endo
    0.42
     Fru
    0.42
    Activations Density 0.019%

    No Known Activations