© 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. 111874
    Prev
    Next
    INDEX
    Explanations

    image and image link

    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
     that
    -2.34
     by
    -1.79
     but
    -1.75
    That
    -1.47
     so
    -1.47
     has
    -1.41
     if
    -1.38
    </h4>
    -1.30
    Also
    -1.30
     these
    -1.28
    POSITIVE LOGITS
    ACIÓN
    1.68
    ación
    1.44
    憮
    1.44
     Variante
    1.44
    蚍
    1.41
     kanker
    1.38
     activit
    1.38
     betek
    1.38
     corriger
    1.38
     fuhr
    1.37
    Activations Density 0.024%

    No Known Activations