© 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. 44845
    Prev
    Next
    INDEX
    Explanations

    do not

    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
    ва
    0.48
    اجة
    0.45
    יו
    0.44
    يو
    0.44
     гори
    0.44
    Mater
    0.44
    يدي
    0.43
     빅뱅
    0.43
    وو
    0.42
    워
    0.42
    POSITIVE LOGITS
    d
    0.50
     adalah
    0.47
     chimique
    0.46
     erity
    0.46
     arab
    0.46
     perilaku
    0.46
     imasmim
    0.45
     elastomer
    0.44
     अद्वितीय
    0.44
    हिनी
    0.44
    Activations Density 0.013%

    No Known Activations