© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    categorized explanations and details

    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
     Moc
    0.35
     respectfully
    0.34
     caution
    0.32
    Kindly
    0.32
     uneasy
    0.31
    Caution
    0.31
     cautionary
    0.31
    ઑ
    0.31
    UMO
    0.30
     Compass
    0.30
    POSITIVE LOGITS
     escolher
    0.41
     veamos
    0.40
     choisissez
    0.39
     veja
    0.36
     june
    0.35
    르면
    0.35
    例子
    0.35
     தேர்வு
    0.35
    形象
    0.34
     這個
    0.34
    Activations Density 0.129%

    No Known Activations