© 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. 10-GEMMASCOPE-RES-131K
    7. 11176
    Prev
    Next
    INDEX
    Explanations

    new development cafés

    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_10/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
     які
    -2.80
     financieras
    -2.50
     sanitarias
    -2.42
     ผม
    -2.41
    葑
    -2.27
    洇
    -2.27
    ۔
    -2.23
    ୈ
    -2.23
    勦
    -2.22
     necesarias
    -2.16
    POSITIVE LOGITS
    {~
    3.11
    ),
    2.55
    -“
    2.25
    毐
    2.23
    至尊
    2.16
    [
    2.14
    }}
    2.05
    atasaray
    2.05
    }$
    1.98
    vantaged
    1.98
    Activations Density 0.000%

    No Known Activations