© 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. 72660
    Prev
    Next
    INDEX
    Explanations

    linux headers

    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
     will
    -1.45
     then
    -1.36
     as
    -1.26
    ↵↵↵
    -1.22
     also
    -1.14
     now
    -1.13
    ↵↵↵↵↵
    -1.10
    ↵↵↵↵
    -1.10
     […]
    -1.06
     because
    -1.05
    POSITIVE LOGITS
    
    1.50
    美国的
    1.34
     стоковые
    1.32
    wieder
    1.30
    
    1.29
    mittags
    1.25
    значення
    1.23
    fertigen
    1.23
    цыі
    1.22
    鱚
    1.21
    Activations Density 0.050%

    No Known Activations