© 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. 15711
    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
    ева
    -1.07
     média
    -0.99
     overview
    -0.93
     gesche
    -0.91
     mè
    -0.90
    Amenities
    -0.90
     saisi
    -0.88
    Затем
    -0.86
     tè
    -0.86
    STALK
    -0.86
    POSITIVE LOGITS
     also
    1.28
    Also
    1.20
    𝑂
    1.09
     by
    1.04
    Before
    1.02
     quantità
    0.98
    alamus
    0.96
    ′,
    0.95
    Give
    0.94
     we
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.