© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65147
    Prev
    Next
    INDEX
    Explanations

    add to this

    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
    ↵↵
    -1.74
     although
    -1.70
     while
    -1.64
    。
    -1.62
    7
    -1.59
    </h1>
    -1.56
    6
    -1.52
    2
    -1.48
     but
    -1.46
    ↵↵↵
    -1.44
    POSITIVE LOGITS
     précie
    1.64
    магазин
    1.62
     météo
    1.60
     prends
    1.55
    ྄
    1.55
     pouss
    1.54
     gâteau
    1.53
     régal
    1.51
     vêtement
    1.51
     vieill
    1.49
    Activations Density 0.024%

    No Known Activations