© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129276
    Prev
    Next
    INDEX
    Explanations

    categories, groups, or lists

    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
     According
    -1.46
     a
    -1.43
     sucht
    -1.41
     Actually
    -1.41
     partes
    -1.40
     Despite
    -1.38
     is
    -1.33
    谙
    -1.31
     By
    -1.28
     new
    -1.22
    POSITIVE LOGITS
    of
    1.76
    还有一
    1.47
     then
    1.39
    oretical
    1.38
     posiblemente
    1.34
    わたしは
    1.33
    ii
    1.31
     другие
    1.30
     [].
    1.23
    很棒
    1.23
    Activations Density 0.060%

    No Known Activations