© 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. 41-GEMMASCOPE-2-RES-262K
    7. 21399
    Prev
    Next
    INDEX
    Explanations

    all, some, three, other

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    版本的
    0.39
    版本
    0.36
    兴趣
    0.35
    示した
    0.34
     Sprachen
    0.34
     Lob
    0.33
     Genes
    0.33
    枃
    0.33
    PEC
    0.32
     Allgemeinen
    0.32
    POSITIVE LOGITS
     things
    0.98
     thing
    0.92
    things
    0.92
     cosas
    0.90
     coisas
    0.90
     bagay
    0.88
     stvari
    0.84
     вещей
    0.79
     şey
    0.77
     вещи
    0.77
    Activations Density 0.000%

    No Known Activations