© 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. 15255
    Prev
    Next
    INDEX
    Explanations

    spaghetti and food words

    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
    夲
    -2.75
    彀
    -2.48
    峮
    -2.47
    就
    -2.42
    푆
    -2.39
    
    -2.38
    他们的
    -2.36
    koszulka
    -2.34
     THEIR
    -2.33
     deres
    -2.31
    POSITIVE LOGITS
    嵯
    2.47
    ]
    2.47
    と感じ
    2.36
     Usually
    2.34
    </h3>
    2.34
     Relatively
    2.30
     During
    2.27
    because
    2.25
     Using
    2.25
     for
    2.25
    Activations Density 0.001%

    No Known Activations