© 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. 89140
    Prev
    Next
    INDEX
    Explanations

    tourism industry, extra oxygen

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

    criminal behavior, property damage

    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
    ച്
    0.49
     MK
    0.46
    Window
    0.46
    č
    0.45
    J
    0.44
    ,
    0.43
     substant
    0.42
    cash
    0.42
    Mk
    0.42
    ac
    0.41
    POSITIVE LOGITS
     против
    0.53
     遅く
    0.52
    भीत
    0.51
    อัน
    0.50
     हाथों
    0.48
     ഉണ്ട്
    0.48
     sentimos
    0.48
    圄
    0.48
     करीब
    0.48
     फल
    0.48
    Activations Density 0.000%

    No Known Activations