© 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-262K
    7. 199910
    Prev
    Next
    INDEX
    Explanations

    Avoiding UI elements and input

    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_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
     메소
    0.52
     Repert
    0.51
    ระบบ
    0.50
    ванный
    0.50
    _
    0.50
    ອາຫານ
    0.49
     userRoutes
    0.49
    🤑
    0.48
    ➩
    0.48
     encontramos
    0.48
    POSITIVE LOGITS
    চিন্ত
    0.44
     Schw
    0.42
     Mills
    0.42
    stalk
    0.41
     Clubs
    0.41
    putting
    0.40
    向
    0.40
     Berk
    0.40
    匆
    0.38
     Schutz
    0.38
    Activations Density 0.005%

    No Known Activations