© 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. 75616
    Prev
    Next
    INDEX
    Explanations

    expect to + verb

    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
    筇
    -2.27
    圌
    -2.06
    ౧
    -2.06
     proporciona
    -1.99
     gigantic
    -1.95
     pourrait
    -1.95
     potrebbe
    -1.89
     colocación
    -1.89
     our
    -1.88
     podría
    -1.88
    POSITIVE LOGITS
    .~(\
    1.73
    there
    1.73
    數字
    1.73
    Not
    1.70
    People
    1.69
    With
    1.66
    There
    1.59
     of
    1.57
     शुर
    1.57
     undangan
    1.56
    Activations Density 0.004%

    No Known Activations