© 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. 48264
    Prev
    Next
    INDEX
    Explanations

    either

    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
     {
    -3.55
     &
    -3.39
    ">
    -3.28
    </b>
    -3.16
    ");
    -2.92
    ');
    -2.58
    ”
    -2.45
    絎
    -2.41
     –
    -2.33
    ”，
    -2.30
    POSITIVE LOGITS
    灩
    2.95
    
    2.52
    </h3>
    2.47
     contemplar
    2.33
     semejante
    2.30
     lesquelles
    2.25
     wichtigen
    2.22
     davidson
    2.20
     ยัง
    2.19
    
    2.16
    Activations Density 0.023%

    No Known Activations