© 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. 22-GEMMASCOPE-RES-131K
    7. 64835
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    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_22/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
    <bos>
    -0.95
     specifics
    -0.88
    紡
    -0.84
     wasn
    -0.81
     therefore
    -0.80
    꽤
    -0.79
    ତ
    -0.79
     details
    -0.77
    不愿意
    -0.75
    不愿
    -0.75
    POSITIVE LOGITS
     Yourself
    1.02
     Lumpur
    0.92
    áu
    0.90
     странице
    0.90
    ник
    0.90
    ⫻
    0.88
     często
    0.87
     are
    0.86
     Moscow
    0.85
    CESO
    0.84
    Activations Density 0.038%

    No Known Activations