© 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. 39939
    Prev
    Next
    INDEX
    Explanations

    exclusive, compatibility, dedicated

    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
     suelen
    -1.17
    剧照
    -1.13
    因为它
    -1.10
     ilustracja
    -1.02
     graciosas
    -1.00
     naše
    -1.00
     máme
    -0.99
     ocupa
    -0.98
     meiner
    -0.97
    ığımız
    -0.97
    POSITIVE LOGITS
     särsk
    1.27
     compatible
    1.27
     compati
    1.08
     idr
    1.07
     compatibility
    1.06
     专
    1.05
     peli
    1.04
    専用の
    1.03
     elsa
    1.03
    Exclusive
    1.03
    Activations Density 0.103%

    No Known Activations