© 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. 73600
    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
     възможно
    -1.08
     fantástica
    -1.07
    InvalidProtocol
    -1.06
    Ķ
    -1.05
    kü
    -1.04
    šķ
    -1.03
    issão
    -1.02
     бампер
    -1.01
    aktery
    -1.00
    frauen
    -1.00
    POSITIVE LOGITS
     certamente
    1.16
    r
    1.10
    or
    1.03
     sicherlich
    1.03
    在乎
    1.02
     QUICK
    1.02
    ak
    1.02
     TIPS
    1.01
     festgestellt
    1.01
    e
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.