© 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. 1378
    Prev
    Next
    INDEX
    Explanations

    risk of closure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     με
    0.57
     ((
    0.51
     ν
    0.49
    ife
    0.49
     caricature
    0.46
     archetype
    0.45
     δ
    0.45
     defined
    0.44
    notFound
    0.44
     எச்ச
    0.43
    POSITIVE LOGITS
     Jó
    0.49
     léz
    0.46
    कार
    0.45
    acijama
    0.45
    เป็นการ
    0.44
    或是
    0.44
    雖
    0.43
    ᄐ
    0.42
     Sparkling
    0.42
    亮的
    0.42
    Activations Density 0.006%

    No Known Activations