© 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. 11884
    Prev
    Next
    INDEX
    Explanations

    capital 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
    </i>
    -2.05
     всички
    -1.88
    '
    -1.79
     =[]
    -1.73
    forKey
    -1.66
    と言われる
    -1.62
     така
    -1.59
    umerable
    -1.57
     lepší
    -1.55
    </h5>
    -1.52
    POSITIVE LOGITS
    𐐪
    2.11
     水墨
    1.88
     bardak
    1.84
    𓋼
    1.82
     respekt
    1.80
     barna
    1.71
     saveiro
    1.69
    ementara
    1.67
    E
    1.67
     setempat
    1.65
    Activations Density 0.015%

    No Known Activations