© 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. 9450
    Prev
    Next
    INDEX
    Explanations

    names of people or places

    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
     Füßen
    -1.78
     their
    -1.62
    彼らは
    -1.55
     Both
    -1.52
    Despite
    -1.52
     with
    -1.51
     both
    -1.48
     first
    -1.44
    They
    -1.44
    Sometimes
    -1.42
    POSITIVE LOGITS
    鸲
    1.66
    cketed
    1.64
    vably
    1.62
    
    1.57
    ᷆
    1.56
    ittaa
    1.56
    ଃ
    1.54
    坶
    1.48
     âgées
    1.47
    ครื่อง
    1.46
    Activations Density 0.048%

    No Known Activations