© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13095
    Prev
    Next
    INDEX
    Explanations

    win/victory/wins

    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
    </h4>
    -1.98
    </u>
    -1.80
    </strong>
    -1.65
    }
    -1.52
    ed
    -1.45
    “
    -1.38
     /
    -1.34
     tremend
    -1.33
    っていきます
    -1.28
    DateTimeFormat
    -1.28
    POSITIVE LOGITS
     aislado
    1.63
     establecer
    1.45
    繆
    1.42
     Gläub
    1.41
    lusconi
    1.41
     Without
    1.38
     онъ
    1.38
    뭔
    1.38
     französ
    1.37
     Versammlung
    1.36
    Activations Density 0.055%

    No Known Activations