© 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. 130253
    Prev
    Next
    INDEX
    Explanations

    identifying themes

    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
     a
    -2.08
    ﹶ
    -1.83
     adalah
    -1.82
     turista
    -1.81
     оценка
    -1.77
    幛
    -1.74
    
    -1.73
    豋
    -1.71
    趿
    -1.70
     almas
    -1.69
    POSITIVE LOGITS
     themes
    1.87
    1
    1.86
    Themes
    1.66
    
    1.66
     квіт
    1.60
    endencies
    1.54
    '
    1.54
    3
    1.53
    </em>
    1.51
     arctic
    1.51
    Activations Density 0.008%

    No Known Activations