© 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. 80123
    Prev
    Next
    INDEX
    Explanations

    "view of", "I can", "lacking formal", "body photo", "based on", "Internal Combustion"

    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
     exceptions
    0.52
     converters
    0.51
     investigations
    0.47
     fire
    0.46
     differential
    0.46
     for
    0.46
     .
    0.46
     children
    0.46
     nour
    0.46
     sale
    0.45
    POSITIVE LOGITS
    iktok
    0.54
    ᱽ
    0.54
     поверну
    0.51
    र्ड
    0.49
    âteau
    0.49
    idän
    0.49
     Kardashian
    0.48
    किस्तानी
    0.46
    স্কার
    0.46
    Matthew
    0.46
    Activations Density 0.016%

    No Known Activations