© 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. 28381
    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
    Both
    -1.61
    Many
    -1.48
    Those
    -1.43
    Several
    -1.41
    Though
    -1.40
    Surprisingly
    -1.40
    While
    -1.39
    Ironically
    -1.39
    When
    -1.38
    Their
    -1.38
    POSITIVE LOGITS
     again
    1.45
     protože
    1.30
     genellikle
    1.23
     mivel
    1.22
     muhte
    1.21
    heses
    1.20
    tiy
    1.20
    salms
    1.19
     ponieważ
    1.19
    occupe
    1.18
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.