© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123988
    Prev
    Next
    INDEX
    Explanations

    Clean up, initialize, structure

    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_10/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
    ↵↵
    -1.80
    ↵↵↵
    -1.72
     decorativa
    -1.54
     когда
    -1.53
    $\
    -1.49
    ">
    -1.39
    ...)
    -1.33
     adecuadas
    -1.32
    ↵↵↵↵
    -1.31
    <b>
    -1.30
    POSITIVE LOGITS
     of
    1.88
    相片
    1.45
     on
    1.41
     khán
    1.32
     and
    1.32
    internalType
    1.31
     for
    1.30
    ߷
    1.30
     vertellen
    1.29
    СЫ
    1.28
    Activations Density 0.007%

    No Known Activations