© 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. 199831
    Prev
    Next
    INDEX
    Explanations

    Diana died, return fee, pair of

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

    locations after re-opening

    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
     跟
    0.57
     먼
    0.51
     하기
    0.49
     모르
    0.49
     చేస్త
    0.48
     보기
    0.48
     ചെയ്യ
    0.47
     걸
    0.47
     ทำ
    0.47
    有一個
    0.47
    POSITIVE LOGITS
    ppe
    0.45
    arct
    0.45
     tentang
    0.42
    LY
    0.41
    functional
    0.41
    PSR
    0.41
    STER
    0.40
     nulla
    0.40
     tecl
    0.39
    क्‍
    0.39
    Activations Density 0.001%

    No Known Activations