© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103644
    Prev
    Next
    INDEX
    Explanations

    technical fields and organizations

    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
    🪆
    -1.60
    簠
    -1.59
    onné
    -1.56
     bepaalde
    -1.55
    Honduras
    -1.55
    玢
    -1.51
    脑袋
    -1.47
     çünkü
    -1.46
    Leírás
    -1.45
    Astronomy
    -1.40
    POSITIVE LOGITS
    This
    2.08
    <em>
    2.08
    i
    1.88
    The
    1.77
    </h2>
    1.75
    ↵↵
    1.75
    For
    1.70
    _
    1.68
    (
    1.68
    Then
    1.66
    Activations Density 0.000%

    No Known Activations