© 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. 128647
    Prev
    Next
    INDEX
    Explanations

    effect of

    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
    
    -1.59
        
    -1.49
     nuov
    -1.49
    .";
    -1.48
     vetro
    -1.45
    ⁎
    -1.45
     ilustracja
    -1.45
    easily
    -1.44
    
    -1.44
     ideen
    -1.41
    POSITIVE LOGITS
    2
    1.91
    </h2>
    1.77
    '
    1.46
     A
    1.43
     --
    1.43
    1
    1.41
    đầm
    1.38
    </em>
    1.37
     That
    1.35
    0
    1.34
    Activations Density 0.027%

    No Known Activations