© 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. 152035
    Prev
    Next
    INDEX
    Explanations

    processed for, someone?, Miami business, something opposite

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

    context length and audience

    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
    عی
    0.50
    読む
    0.48
    وء
    0.48
     хочет
    0.46
    씬
    0.46
    суа
    0.46
    すと
    0.46
    忘了
    0.45
    ﷲ
    0.45
     سوال
    0.45
    POSITIVE LOGITS
     elektrische
    0.57
     gef
    0.56
     pouches
    0.56
     lanz
    0.52
     apricots
    0.52
    នៅលើ
    0.51
     ני
    0.51
     ATMs
    0.51
     arteries
    0.50
     IOS
    0.49
    Activations Density 0.001%

    No Known Activations