© 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. 99878
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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
     both
    -1.86
     only
    -1.69
     just
    -1.60
     them
    -1.58
    0
    -1.54
     ensures
    -1.53
     gives
    -1.52
     on
    -1.52
     new
    -1.48
     promotes
    -1.48
    POSITIVE LOGITS
    actéristi
    1.80
    缑
    1.60
    ﮏ
    1.57
    lehnt
    1.55
     valentín
    1.52
    锨
    1.52
    ﮯ
    1.51
     '',
    1.50
    ਃ
    1.46
    蒾
    1.45
    Activations Density 0.168%

    No Known Activations