© 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. 48030
    Prev
    Next
    INDEX
    Explanations

    directions and extremities

    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
    </h3>
    -1.80
    起来的
    -1.59
     ‘‘
    -1.59
     също
    -1.55
    </i>
    -1.50
    matically
    -1.45
    脸色
    -1.44
    https
    -1.40
    まさ
    -1.37
     ¨
    -1.35
    POSITIVE LOGITS
     it
    2.27
    end
    1.70
     this
    1.70
     on
    1.68
     for
    1.63
     we
    1.54
     sobrevivir
    1.52
    晚安
    1.52
     desire
    1.52
     Kühlschrank
    1.47
    Activations Density 0.012%

    No Known Activations