© 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. 130951
    Prev
    Next
    INDEX
    Explanations

    diagrams and circuit diagrams

    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
     möjlighet
    -1.37
    :
    -1.08
    pantalon
    -1.08
    哪个
    -1.05
     robić
    -1.05
     this
    -1.02
     that
    -1.02
    以上です
    -1.02
    じゃなくて
    -0.99
     possibilité
    -0.98
    POSITIVE LOGITS
     ток
    1.20
     pido
    1.06
     finalmente
    1.05
    lectro
    1.03
     Ärz
    1.01
    ленно
    1.00
    ungalows
    0.99
    Kilder
    0.99
     diversos
    0.99
     diagram
    0.99
    Activations Density 0.047%

    No Known Activations