© 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. 110868
    Prev
    Next
    INDEX
    Explanations

    the name Bennett

    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
    渽
    -2.66
     enviable
    -2.63
    ৢ
    -2.55
     Opens
    -2.47
     помогает
    -2.45
    鬭
    -2.45
     этими
    -2.39
     tasas
    -2.39
    遑
    -2.36
     сказал
    -2.31
    POSITIVE LOGITS
    $
    3.27
    而来
    2.77
    as
    2.41
    '
    2.39
    U
    2.38
    to
    2.34
    </h2>
    2.25
    趼
    2.25
                    
    2.25
     ältere
    2.23
    Activations Density 0.002%

    No Known Activations