© 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-65K
    7. 56710
    Prev
    Next
    INDEX
    Explanations

    contrasting statements and surprising outcomes

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     तपाई
    0.48
     toolbox
    0.46
     headache
    0.45
    getData
    0.44
    <start_of_image>
    0.44
     PR
    0.43
     interconnected
    0.43
     Continuing
    0.43
     scoprire
    0.43
     CO
    0.43
    POSITIVE LOGITS
     الذي
    0.51
     GoObject
    0.46
    uttab
    0.46
    pyrazin
    0.45
     الذين
    0.44
    వృద్ధి
    0.43
     رباع
    0.43
    袅
    0.43
     توزيع
    0.42
    ари
    0.42
    Activations Density 0.008%

    No Known Activations