© 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. 70106
    Prev
    Next
    INDEX
    Explanations

    ruler blog

    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
     if
    -2.38
     even
    -1.82
     until
    -1.79
     at
    -1.79
     there
    -1.79
     while
    -1.52
     If
    -1.48
     without
    -1.47
     although
    -1.46
    even
    -1.46
    POSITIVE LOGITS
     autres
    1.70
    其他
    1.69
    และ
    1.67
    malige
    1.60
     anderen
    1.59
     nimmer
    1.48
     autre
    1.45
    ections
    1.45
    อื่น
    1.42
    ：……
    1.38
    Activations Density 0.143%

    No Known Activations