© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8058
    Prev
    Next
    INDEX
    Explanations

    require statements and code modules

    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
    Doodle
    -1.38
     an
    -1.34
     because
    -1.33
     this
    -1.33
    
    -1.24
     pemer
    -1.21
    ᠶ
    -1.21
    ࿆
    -1.20
     ESTADO
    -1.20
     aliran
    -1.20
    POSITIVE LOGITS
    Our
    1.51
    six
    1.48
    Your
    1.45
     cinq
    1.42
     пять
    1.40
    Nice
    1.35
    Which
    1.33
     шесть
    1.32
    Such
    1.32
     рабочих
    1.30
    Activations Density 0.014%

    No Known Activations