© 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-262K
    7. 13156
    Prev
    Next
    INDEX
    Explanations

    lists and structure

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     luggage
    0.48
     పిల్ల
    0.45
     प्रमुख
    0.42
    子女
    0.42
     děti
    0.39
    durationType
    0.39
     అంశ
    0.38
     firewood
    0.38
    apadani
    0.38
    ﻩ
    0.38
    POSITIVE LOGITS
     veut
    0.44
     Tabor
    0.42
    wier
    0.40
    weiter
    0.40
     vermelho
    0.40
    win
    0.39
    hnt
    0.39
    ubi
    0.39
     Wettbewer
    0.39
    phi
    0.38
    Activations Density 0.726%

    No Known Activations