© 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. 52641
    Prev
    Next
    INDEX
    Explanations

    Whatever happened, it implies

    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
     цих
    0.50
     einzelnen
    0.50
    ٽ
    0.49
     respectivos
    0.45
     інших
    0.45
     اضافی
    0.44
     privati
    0.44
     innych
    0.43
     limitée
    0.43
     التح
    0.42
    POSITIVE LOGITS
    am
    0.52
    pan
    0.52
    book
    0.48
    show
    0.48
    c
    0.47
    holder
    0.47
    d
    0.46
    cat
    0.46
     explaining
    0.46
    dump
    0.46
    Activations Density 0.004%

    No Known Activations