© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43172
    Prev
    Next
    INDEX
    Explanations

    natural product or hero

    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
     about
    -1.59
    tocks
    -1.43
     ihan
    -1.41
    gradable
    -1.36
    artment
    -1.32
    \-
    -1.30
     illetve
    -1.29
    corer
    -1.29
    áncer
    -1.27
    baño
    -1.27
    POSITIVE LOGITS
    </b>
    1.38
     infância
    1.36
     ถ้า
    1.34
     tradição
    1.34
     mantend
    1.33
     теперь
    1.32
     população
    1.29
     Already
    1.27
     criança
    1.27
    vettes
    1.27
    Activations Density 0.087%

    No Known Activations