© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    foreign language punctuation and titles

    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
     $
    -1.10
     .
    -0.97
     obszar
    -0.94
    😮
    -0.92
    beforeAll
    -0.91
        
    -0.91
     Zahlen
    -0.90
    urige
    -0.89
     '.
    -0.89
    ‼️
    -0.89
    POSITIVE LOGITS
     and
    1.37
    Hvordan
    1.21
     apagar
    1.20
    Hvad
    1.20
    を広
    1.18
     eccell
    1.13
    Få
    1.13
     mencionado
    1.12
    Hvem
    1.11
    Vezi
    1.09
    Activations Density 0.000%

    No Known Activations