© 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. 22-GEMMASCOPE-RES-131K
    7. 34654
    Prev
    Next
    INDEX
    Explanations

    adverbs (mainly Russian suffixes)

    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_22/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
    းက
    -1.94
    趼
    -1.86
     pencarian
    -1.84
     for
    -1.81
     of
    -1.81
    ࿙
    -1.75
    퐹
    -1.70
     paredes
    -1.70
    翆
    -1.70
    Hilsen
    -1.67
    POSITIVE LOGITS
    \
    2.03
    ”
    1.91
    f
    1.81
    ta
    1.74
    re
    1.72
    en
    1.71
    $
    1.70
    𝑒
    1.66
    [
    1.66
    j
    1.65
    Activations Density 0.004%

    No Known Activations