© 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. 39340
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    americanas
    -1.07
                
    -1.06
    </em>
    -1.06
     also
    -1.05
     these
    -1.02
    除此之外
    -0.99
     better
    -0.98
     was
    -0.96
     for
    -0.95
     betreffenden
    -0.95
    POSITIVE LOGITS
     рестай
    1.28
     wzglę
    1.27
     złota
    1.21
     muere
    1.21
     ofta
    1.13
     olvidado
    1.12
     colgante
    1.11
    怂
    1.10
     obligado
    1.10
     rembour
    1.08
    Activations Density 0.035%

    No Known Activations