© 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. 9207
    Prev
    Next
    INDEX
    Explanations

    foreign language and code constructs

    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
     chronicle
    0.31
     integrations
    0.28
     কর্তা
    0.27
     trzy
    0.26
     threefold
    0.26
     ۋە
    0.26
     momentous
    0.25
    
    0.25
    Integration
    0.25
    밸
    0.25
    POSITIVE LOGITS
    ató
    0.33
     కూడా
    0.32
     പോലും
    0.32
    🤫
    0.31
    これも
    0.31
     utan
    0.30
    putnik
    0.29
    ៕
    0.29
    ckså
    0.29
    isał
    0.29
    Activations Density 0.051%

    No Known Activations