© 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. 47918
    Prev
    Next
    INDEX
    Explanations

    technical and scientific contexts

    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
    ’
    -2.20
    …..
    -2.13
    ;
    -1.83
    ↵↵↵↵
    -1.75
    нцип
    -1.74
    …»
    -1.74
    ….
    -1.71
    k
    -1.70
    ……」
    -1.70
    ,…
    -1.70
    POSITIVE LOGITS
     fondée
    2.09
     overarching
    2.03
    
    1.98
    蛱
    1.96
     fotografii
    1.95
    ではある
    1.95
     casamento
    1.95
     they
    1.95
     namorado
    1.91
    
    1.91
    Activations Density 0.000%

    No Known Activations