© 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. 56723
    Prev
    Next
    INDEX
    Explanations

    making a move you

    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
    redraw
    0.46
     ярко
    0.46
     проце
    0.45
    怸
    0.45
     fichiers
    0.42
    应用于
    0.42
     निर्ण
    0.42
    applic
    0.41
     teinture
    0.41
    醌
    0.41
    POSITIVE LOGITS
     race
    0.51
     mod
    0.50
     GENER
    0.49
     lone
    0.48
     geo
    0.48
     has
    0.47
     on
    0.47
     str
    0.46
     linear
    0.46
     hash
    0.46
    Activations Density 0.015%

    No Known Activations