© 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. 73707
    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
     to
    -1.63
    providedIn
    -1.62
     or
    -1.49
     leksikon
    -1.40
     endforeach
    -1.35
     later
    -1.34
    </tfoot>
    -1.32
     you
    -1.27
    When
    -1.25
     When
    -1.23
    POSITIVE LOGITS
    )=>{
    1.46
    鹉
    1.30
     remplacer
    1.30
    鴬
    1.28
    ↵
    1.28
    fails
    1.27
    achieve
    1.27
    &
    1.26
     estándares
    1.25
     bénéficient
    1.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.