© 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. 40-GEMMASCOPE-2-RES-65K
    7. 56323
    Prev
    Next
    INDEX
    Explanations

    finite fields and Fc region

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     이론
    0.39
    ంద
    0.39
     견
    0.37
     पुरा
    0.37
    ంబ
    0.37
     대한
    0.37
    谴
    0.37
     Л
    0.37
    Failure
    0.37
     ἔ
    0.37
    POSITIVE LOGITS
     scalars
    0.51
     campo
    0.46
     سفارش
    0.45
     Fc
    0.45
     constante
    0.45
     field
    0.45
     característica
    0.44
     karakteristik
    0.43
     characteristic
    0.43
     Scalar
    0.43
    Activations Density 0.016%

    No Known Activations