© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67246
    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
    이다
    -1.10
    pyl
    -1.00
     Depor
    -0.98
    是一款
    -0.95
     MÉXICO
    -0.94
     hanno
    -0.94
    𖥧
    -0.93
     AGUA
    -0.91
     UNIVERSIT
    -0.91
     aren
    -0.90
    POSITIVE LOGITS
     with
    1.15
     üblichen
    1.08
    Why
    1.05
     one
    1.02
     управління
    0.96
     Gehalt
    0.94
     There
    0.93
     clover
    0.92
     sharper
    0.91
    metery
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.