© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    examples following including

    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
     
    -1.91
     same
    -1.84
    )
    -1.77
    1
    -1.77
    </h3>
    -1.75
    是
    -1.63
    。”
    -1.60
    のは
    -1.58
     یا
    -1.58
    所有
    -1.55
    POSITIVE LOGITS
     the
    2.45
    衚
    1.96
     whom
    1.87
     that
    1.84
     ſch
    1.78
     skillfully
    1.77
     where
    1.76
     rijden
    1.75
    
    1.73
     when
    1.73
    Activations Density 0.021%

    No Known Activations