© 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. 61139
    Prev
    Next
    INDEX
    Explanations

    publication status

    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
    馀
    -1.60
     haughty
    -1.59
    ”、“
    -1.53
    hline
    -1.51
    谕
    -1.50
    v
    -1.50
    涣
    -1.50
     již
    -1.49
    撷
    -1.45
     of
    -1.43
    POSITIVE LOGITS
     about
    1.61
    läng
    1.55
    ."));
    1.52
    woorden
    1.51
     ganti
    1.48
     kompatibel
    1.46
    同學
    1.45
    inerario
    1.45
     respecting
    1.45
    那麼
    1.43
    Activations Density 0.074%

    No Known Activations