© 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. 22-GEMMASCOPE-RES-131K
    7. 26367
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.83
     Why
    -1.62
     With
    -1.55
     their
    -1.54
     với
    -1.48
     or
    -1.38
     dengan
    -1.38
     unique
    -1.37
     have
    -1.36
     incurred
    -1.36
    POSITIVE LOGITS
    <bos>
    1.86
     avo
    1.48
     vingt
    1.45
    んでも
    1.44
    mainly
    1.36
    gencias
    1.34
     heridos
    1.33
     kostenlose
    1.30
    も含
    1.28
    primarily
    1.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.