© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15520
    Prev
    Next
    INDEX
    Explanations

    reporting quoted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h2>
    -1.86
    毉
    -1.61
    </em>
    -1.52
    ܔ
    -1.52
    ጧ
    -1.45
    觉得
    -1.42
    ⍽
    -1.41
    bujete
    -1.40
     قبل
    -1.39
    一些
    -1.38
    POSITIVE LOGITS
    s
    1.58
    勿論
    1.56
     дов
    1.45
    人也
    1.44
     according
    1.40
    ：【
    1.39
    OLUTION
    1.33
    er
    1.33
    on
    1.32
    昔から
    1.32
    Activations Density 0.031%

    No Known Activations