© 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. 113248
    Prev
    Next
    INDEX
    Explanations

    South Wales

    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
    鯔
    -2.23
    Bisa
    -2.20
    뿅
    -2.17
    hamilan
    -2.13
    風格
    -2.03
    𖡼
    -2.03
    細節
    -2.02
    Rumah
    -1.99
    與
    -1.96
    Semua
    -1.95
    POSITIVE LOGITS
     of
    2.63
    “
    2.55
    蓠
    2.39
    在她
    2.30
    rii
    1.94
    睃
    1.91
    clearly
    1.91
    ts
    1.90
    ↵
    1.88
    掀
    1.87
    Activations Density 0.006%

    No Known Activations