© 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. 84269
    Prev
    Next
    INDEX
    Explanations

    HTML entities and query parameters

    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
     \
    -2.75
    ेमाल
    -2.66
    guigu
    -2.45
    焄
    -2.44
    会儿
    -2.44
    鈊
    -2.41
    睒
    -2.41
     शुर
    -2.30
    してみました
    -2.30
     gavetas
    -2.28
    POSITIVE LOGITS
    amp
    3.42
    ⸺
    3.02
    We
    2.81
    in
    2.64
    ul
    2.59
    ia
    2.45
    out
    2.41
    ir
    2.39
    to
    2.38
    z
    2.38
    Activations Density 0.002%

    No Known Activations