© 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. 44614
    Prev
    Next
    INDEX
    Explanations

    how you win

    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
     всего
    0.47
     больше
    0.42
     ώ
    0.41
     ослож
    0.40
     සිදු
    0.38
    े
    0.38
     grapevine
    0.38
     incomplète
    0.37
     фирмы
    0.37
    வாகும்
    0.37
    POSITIVE LOGITS
    $,
    0.48
     राजनीतिक
    0.47
    ），
    0.46
    ,@
    0.45
     क्षण
    0.45
    ，
    0.44
     meaningfully
    0.42
     absurdity
    0.42
     يقول
    0.42
     phrasing
    0.42
    Activations Density 0.032%

    No Known Activations