© 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. 26860
    Prev
    Next
    INDEX
    Explanations

    ports and interfaces

    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
    
    -1.05
     Redewendung
    -1.05
    ネック
    -1.05
    Карьера
    -1.05
    ουσ
    -1.03
    時から
    -1.02
     Wortes
    -0.99
    Entonces
    -0.99
     terceira
    -0.96
    Fonto
    -0.95
    POSITIVE LOGITS
     ports
    1.33
    output
    1.25
     interface
    1.20
     port
    1.20
     these
    1.16
    anschluss
    1.16
     connections
    1.13
     интерфей
    1.10
    ёх
    1.07
    port
    1.05
    Activations Density 0.098%

    No Known Activations