© 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. 200176
    Prev
    Next
    INDEX
    Explanations

    stumbling, lost, abused

    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
    owied
    0.46
    robespierre
    0.46
    manes
    0.46
     продуктов
    0.44
    ўцаў
    0.43
    माश
    0.43
     ইপিআর
    0.43
    𝚔
    0.42
    elola
    0.42
     மன்னி
    0.42
    POSITIVE LOGITS
     Number
    0.51
     number
    0.49
     and
    0.47
    .
    0.47
     or
    0.46
     Traditional
    0.46
     [
    0.45
     teaspoon
    0.45
     bulb
    0.45
     Serial
    0.45
    Activations Density 0.008%

    No Known Activations