© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38912
    Prev
    Next
    INDEX
    Explanations

    Central followed by proper nouns

    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
    '
    -3.36
     extremamente
    -3.06
    栳
    -2.81
     fazia
    -2.81
    咙
    -2.72
    鷙
    -2.58
    
    -2.55
    餮
    -2.53
    癭
    -2.52
     parecia
    -2.45
    POSITIVE LOGITS
    蒹
    3.63
    most
    3.59
    ୌ
    3.50
    
    3.36
    Однако
    3.30
    犇
    3.13
    ization
    3.08
    Just
    3.05
    Many
    3.00
    目前的
    2.94
    Activations Density 0.022%

    No Known Activations