© 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. 64662
    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
     after
    -1.63
     if
    -1.56
     when
    -1.50
     any
    -1.47
     may
    -1.38
     because
    -1.36
     before
    -1.34
     although
    -1.24
     so
    -1.20
    ̮
    -1.20
    POSITIVE LOGITS
     Becomes
    1.39
     Promotes
    1.33
     frequentemente
    1.30
     AMAZING
    1.27
     sumptuous
    1.26
     unmistak
    1.20
     opulent
    1.20
     innumer
    1.19
     tumultuous
    1.18
     arrêter
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.