© 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. 160081
    Prev
    Next
    INDEX
    Explanations

    daily activities and region permits

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

    account details

    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
     것처럼
    0.48
     နှစ်
    0.48
    bür
    0.47
    బ్‌
    0.46
     सर्किल
    0.44
    ély
    0.44
     Reforms
    0.44
    ᄒ
    0.44
    bane
    0.43
    Sprite
    0.43
    POSITIVE LOGITS
     nokt
    0.51
    被人
    0.46
     aqua
    0.45
     daun
    0.45
     Lihat
    0.45
    نی
    0.44
     I
    0.44
    regarding
    0.44
     khawatir
    0.43
    רה
    0.43
    Activations Density 0.000%

    No Known Activations