© 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. 120864
    Prev
    Next
    INDEX
    Explanations

    burning as, consistency by

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

    promove, promote, incite

    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
    基本的に
    0.47
    et
    0.47
    กด
    0.46
    uos
    0.46
     அனை
    0.45
     fluctuating
    0.45
     غالب
    0.45
    ⌯
    0.45
     ø
    0.43
    設定
    0.43
    POSITIVE LOGITS
     promove
    0.48
     स्टूडेंट्स
    0.48
     estimular
    0.48
    投手
    0.47
     samping
    0.46
     promover
    0.46
    祷
    0.46
     juntos
    0.45
     ремонт
    0.45
     rencontrer
    0.45
    Activations Density 0.001%

    No Known Activations