© 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. 22298
    Prev
    Next
    INDEX
    Explanations

    version specifiers

    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
     one
    -1.88
     all
    -1.71
     through
    -1.68
     because
    -1.58
     may
    -1.55
     two
    -1.43
     iniciativas
    -1.37
     nestled
    -1.35
     might
    -1.34
     out
    -1.34
    POSITIVE LOGITS
     использу
    1.44
    seitige
    1.38
    hören
    1.37
     kurzem
    1.37
     tio
    1.36
    <bos>
    1.34
     recent
    1.33
     estabilidad
    1.33
    führen
    1.32
     ack
    1.32
    Activations Density 0.159%

    No Known Activations