© 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. 10-GEMMASCOPE-RES-131K
    7. 808
    Prev
    Next
    INDEX
    Explanations

    proven effectiveness

    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
    
    -2.45
    あるので
    -2.36
    ]
    -2.34
    
    -2.33
     cuando
    -2.33
     continúas
    -2.33
    ations
    -2.22
    蚤
    -2.20
     For
    -2.17
    t
    -2.14
    POSITIVE LOGITS
    ↵
    2.70
    结语
    2.66
    *"
    2.55
    "}}>
    2.55
    袮
    2.44
     "
    2.41
    an
    2.31
    <em>
    2.30
    ン
    2.17
    ly
    2.16
    Activations Density 0.004%

    No Known Activations