© 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. 8569
    Prev
    Next
    INDEX
    Explanations

    response or res in code

    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
     or
    -2.16
     our
    -1.70
     from
    -1.69
     или
    -1.58
     Excellent
    -1.55
     all
    -1.54
     my
    -1.52
     the
    -1.50
     и
    -1.48
     Almost
    -1.48
    POSITIVE LOGITS
     quoc
    1.78
    ZAR
    1.69
     geld
    1.61
    這
    1.60
     serre
    1.58
     horloge
    1.58
    鉺
    1.57
    
    1.54
    අ
    1.49
    這個
    1.48
    Activations Density 0.001%

    No Known Activations