© 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. 34-GEMMASCOPE-RES-131K
    4. 116056
    Prev
    Next
    INDEX
    Explanations

    patch

    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_34/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
    ✥
    -0.76
     `<
    -0.74
     huellas
    -0.73
     والم
    -0.72
    atist
    -0.71
    thera
    -0.71
     Winnipeg
    -0.70
    لينا
    -0.70
    Viola
    -0.70
     вжи
    -0.70
    POSITIVE LOGITS
     Patch
    2.91
    Patch
    2.70
     patch
    2.28
    patch
    2.23
     PATCH
    2.13
    PATCH
    2.06
     patches
    1.73
     Patches
    1.72
    Patches
    1.56
    patches
    1.45
    Activations Density 0.036%

    No Known Activations