© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 187489
    Prev
    Next
    INDEX
    Explanations

    pancake sizes

    np_acts-logits-general · gemini-2.5-flash-lite

    note crashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ่
    0.52
    ليل
    0.51
    عهد
    0.49
     comprendre
    0.49
    林
    0.48
    ہد
    0.47
    مدة
    0.47
     Spreadsheet
    0.46
     jamais
    0.45
    しい
    0.45
    POSITIVE LOGITS
    骁
    0.52
     ກຳ
    0.49
     요청
    0.49
     Özellikle
    0.48
    ottle
    0.48
    iffy
    0.47
     बाय
    0.47
     రుణ
    0.47
     ्
    0.46
     बाइ
    0.46
    Activations Density 0.001%

    No Known Activations