© 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. 44862
    Prev
    Next
    INDEX
    Explanations

    kilo, kg, bud, simple, be, even

    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
     reacciones
    0.41
     dłu
    0.41
    靗
    0.41
     vertrou
    0.40
     recognises
    0.40
     rejest
    0.39
     जेसीबी
    0.39
    🖉
    0.39
     odpow
    0.39
     restricciones
    0.39
    POSITIVE LOGITS
    afa
    0.45
    mental
    0.44
    ь
    0.44
    ving
    0.44
    ranial
    0.44
    converter
    0.43
     physiologically
    0.43
    v
    0.43
    voi
    0.43
    va
    0.43
    Activations Density 0.003%

    No Known Activations