© 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. 127991
    Prev
    Next
    INDEX
    Explanations

    various causes of a problem

    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
    ;
    -1.67
     I
    -1.64
    ｍ
    -1.55
    in
    -1.54
    日発売
    -1.48
    l
    -1.47
    its
    -1.45
    all
    -1.45
    you
    -1.44
    p
    -1.44
    POSITIVE LOGITS
     comentário
    2.14
    俅
    1.95
    を使用した
    1.95
     amortecedor
    1.91
     parachoque
    1.89
     laço
    1.88
    饪
    1.86
     dificuldades
    1.83
     comunicação
    1.81
    赑
    1.81
    Activations Density 0.003%

    No Known Activations