© 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. 11137
    Prev
    Next
    INDEX
    Explanations

    abbreviations followed by parentheses

    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
     \
    -2.17
     If
    -2.14
    A
    -2.13
    It
    -2.11
    :
    -2.03
     Not
    -1.89
    に戻る
    -1.88
     Also
    -1.87
     By
    -1.82
    R
    -1.82
    POSITIVE LOGITS
    ᜀ
    1.96
    <bos>
    1.92
    และ
    1.92
     remé
    1.88
    şık
    1.84
     rése
    1.83
    蚰
    1.77
     personalización
    1.75
     camiset
    1.74
    焢
    1.73
    Activations Density 0.139%

    No Known Activations