© 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. 98707
    Prev
    Next
    INDEX
    Explanations

    ftp client or mail server

    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
    Negative Logits
    ㈡
    -1.23
     опять
    -1.23
     espanhol
    -1.23
    趼
    -1.22
    嘁
    -1.18
     independente
    -1.17
    Biografía
    -1.13
     judicia
    -1.13
     énergé
    -1.12
    teit
    -1.10
    POSITIVE LOGITS
     each
    1.69
    .”
    1.23
     them
    1.16
     often
    1.13
     so
    1.13
    着一
    1.12
     Georgia
    1.10
     каждо
    1.10
     from
    1.09
     like
    1.09
    Activations Density 0.105%

    No Known Activations