© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85842
    Prev
    Next
    INDEX
    Explanations

    postseason tournaments and playoffs

    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
    am
    -1.69
    including
    -1.69
    v
    -1.69
    possibly
    -1.67
    such
    -1.58
     способы
    -1.57
    b
    -1.55
    has
    -1.52
    g
    -1.50
    those
    -1.48
    POSITIVE LOGITS
    ."
    1.87
     perintah
    1.60
    aulted
    1.49
    茘
    1.49
     it
    1.48
    静岡
    1.36
    ähkö
    1.35
    türk
    1.34
    nienia
    1.34
    şk
    1.34
    Activations Density 0.023%

    No Known Activations