© 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. 31-GEMMASCOPE-2-RES-65K
    7. 49123
    Prev
    Next
    INDEX
    Explanations

    code formatting block

    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_31_width_65k_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
     станции
    0.48
     mân
    0.45
     χρόνια
    0.45
     녹
    0.45
     zmienia
    0.44
    </h1>
    0.44
     mannequin
    0.44
     lesbian
    0.43
     Charl
    0.43
    ານ
    0.43
    POSITIVE LOGITS
    issenschaft
    0.46
    ЛО
    0.44
    wissenschaft
    0.44
    لم
    0.44
    راف
    0.44
    difficulty
    0.44
    Difficulty
    0.43
    ков
    0.43
    }$-(
    0.42
    ال
    0.42
    Activations Density 0.012%

    No Known Activations