© 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-262K
    7. 9106
    Prev
    Next
    INDEX
    Explanations

    list headings and examples

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    nya
    0.37
    CLAIM
    0.32
    oliath
    0.32
    nio
    0.32
     Ligue
    0.32
    ၣ်
    0.32
     Claim
    0.31
    y
    0.31
    ujesz
    0.31
    ørende
    0.31
    POSITIVE LOGITS
     austere
    0.35
    种种
    0.34
    프트
    0.33
    铿
    0.33
     mollus
    0.32
    骅
    0.31
     unsettling
    0.31
     crashes
    0.30
     사항
    0.30
     Messrs
    0.30
    Activations Density 0.001%

    No Known Activations