© 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. 66747
    Prev
    Next
    INDEX
    Explanations

    so that

    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
    ’，
    -1.89
    ၟ
    -1.73
    d
    -1.68
    <bos>
    -1.63
    ～。
    -1.62
    ￨
    -1.56
     deras
    -1.55
    趼
    -1.55
    licitations
    -1.55
    ですが
    -1.54
    POSITIVE LOGITS
     that
    2.72
     they
    2.52
     you
    2.34
     It
    1.95
    明日は
    1.88
     we
    1.87
    盌
    1.85
    を目指す
    1.83
    ができます
    1.81
    を選ぶ
    1.79
    Activations Density 0.023%

    No Known Activations