© 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. 27297
    Prev
    Next
    INDEX
    Explanations

    conditional verb endings

    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
    〜！
    -1.75
    Эти
    -1.69
    MILLISECONDS
    -1.66
    ꈊ
    -1.61
    韃
    -1.59
    〜。
    -1.55
    ﾐ
    -1.55
     masaj
    -1.54
    ၜ
    -1.53
    📔
    -1.52
    POSITIVE LOGITS
    {
    1.82
    (
    1.77
    '
    1.75
    ↵↵
    1.72
     be
    1.64
     are
    1.45
    ’
    1.37
    …
    1.34
    obten
    1.34
    in
    1.32
    Activations Density 0.010%

    No Known Activations