© 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. 66852
    Prev
    Next
    INDEX
    Explanations

    GPL software licenses

    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
    
    -2.39
    
    -2.33
    霂
    -2.33
    媗
    -2.27
     нього
    -2.22
    इटम
    -2.22
    絝
    -2.17
    ݯ
    -2.14
     Then
    -2.11
    </th>
    -2.05
    POSITIVE LOGITS
    1
    2.41
    2
    2.33
    s
    2.23
     للف
    2.05
    9
    1.99
     gezogen
    1.98
    >
    1.98
     Attractive
    1.96
    ﮨ
    1.95
     genoux
    1.92
    Activations Density 0.021%

    No Known Activations