© 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. 174440
    Prev
    Next
    INDEX
    Explanations

    summer fun

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

    applying after

    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
     除
    0.51
    cheon
    0.48
     असंख्य
    0.47
    attacks
    0.46
     Angriff
    0.46
    als
    0.45
     Zodiac
    0.45
     لينك
    0.45
     線
    0.45
     সরাসরি
    0.45
    POSITIVE LOGITS
     awal
    0.55
    ິດຕ
    0.54
     manage
    0.49
     headless
    0.48
     managing
    0.48
    IDAD
    0.48
     saan
    0.47
     moim
    0.46
     управлять
    0.46
     mam
    0.45
    Activations Density 0.001%

    No Known Activations