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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9973
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    艄
    -1.46
    Skocz
    -1.41
    (!__
    -1.40
    踯
    -1.40
     hecta
    -1.33
    ’
    -1.29
     coupé
    -1.29
     "]";
    -1.28
     bleus
    -1.27
    と思
    -1.26
    POSITIVE LOGITS
     myös
    1.70
     numerosas
    1.65
     tudi
    1.59
     Obtén
    1.54
     både
    1.48
     "
    1.47
     through
    1.45
     by
    1.45
     három
    1.43
     refugiados
    1.43
    Activations Density 0.033%

    No Known Activations