© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48434
    Prev
    Next
    INDEX
    Explanations

    C++ namespaces and declarations

    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
     to
    -1.59
    .
    -1.49
     --
    -1.43
     G
    -1.37
     damals
    -1.33
     S
    -1.32
    -
    -1.30
    ---
    -1.30
     P
    -1.27
    --
    -1.27
    POSITIVE LOGITS
     cairan
    1.78
     rempliss
    1.66
    TryDecode
    1.61
     jossa
    1.59
    縂
    1.55
    Vendredi
    1.50
     중요
    1.48
    翾
    1.48
     zeggen
    1.47
    Lundi
    1.47
    Activations Density 0.045%

    No Known Activations