© 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. 8482
    Prev
    Next
    INDEX
    Explanations

    university names

    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
     your
    -1.86
    就行了
    -1.75
    神
    -1.67
    就可以了
    -1.59
     commerces
    -1.57
     projets
    -1.49
     السياس
    -1.48
    举动
    -1.48
     compagnies
    -1.46
     are
    -1.45
    POSITIVE LOGITS
     with
    2.28
    ӥ
    1.64
     með
    1.64
    ’，
    1.63
     rencontr
    1.55
    توضیحات
    1.55
    🕗
    1.51
    ”،
    1.49
     Furthermore
    1.47
    roughts
    1.45
    Activations Density 0.146%

    No Known Activations