© 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. 22-GEMMASCOPE-RES-131K
    7. 68441
    Prev
    Next
    INDEX
    Explanations

    self discovery

    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
     at
    -1.94
     in
    -1.73
     all
    -1.70
     still
    -1.58
     these
    -1.55
     because
    -1.52
     every
    -1.48
     by
    -1.48
     as
    -1.48
     after
    -1.47
    POSITIVE LOGITS
    為に
    1.66
    ほら
    1.62
    ところに
    1.50
    割と
    1.45
    ようで
    1.42
    あー
    1.41
    のエ
    1.38
    感じで
    1.38
    すっ
    1.38
    こいつ
    1.36
    Activations Density 1.600%

    No Known Activations