© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38845
    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
     воздух
    -1.05
    dungen
    -0.91
    şek
    -0.90
    ométrique
    -0.90
    cestors
    -0.90
    zdo
    -0.90
     them
    -0.87
    cora
    -0.87
    Já
    -0.86
    şu
    -0.86
    POSITIVE LOGITS
     and
    1.30
     culturali
    1.05
     followed
    0.94
     entrain
    0.91
    楽しめます
    0.90
    ⓷
    0.87
     offseason
    0.87
     airsoft
    0.84
    ėk
    0.84
     있으며
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.