© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13470
    Prev
    Next
    INDEX
    Explanations

    "wallet" or "bolso"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᆻ
    0.38
     عند
    0.38
     কোয়া
    0.38
    ฺ
    0.38
     centerpiece
    0.36
    鋰
    0.35
    med
    0.35
     pottery
    0.35
     department
    0.35
    spaper
    0.35
    POSITIVE LOGITS
    Wallet
    0.43
    巩
    0.38
    地址
    0.38
    钱包
    0.37
     wallet
    0.37
    㥆
    0.35
    ENABLE
    0.35
     Aplikasi
    0.34
     अधिव
    0.34
     bolso
    0.34
    Activations Density 0.000%

    No Known Activations