© 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. 70993
    Prev
    Next
    INDEX
    Explanations

    evaluating educational practices

    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
    🧫
    -1.93
    🚰
    -1.89
     mengumumkan
    -1.87
    🧵
    -1.85
    🪛
    -1.82
     memasuki
    -1.78
     now
    -1.73
    没能
    -1.71
    🔧
    -1.71
     frankfurt
    -1.70
    POSITIVE LOGITS
     дошко
    2.36
     Glaubens
    2.06
    🧌
    1.92
    𝗼
    1.87
     others
    1.79
    🪢
    1.78
     schöne
    1.74
    걍
    1.73
     Kollegen
    1.72
     anderen
    1.70
    Activations Density 1.375%

    No Known Activations