© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261415
    Prev
    Next
    INDEX
    Explanations

    dishonesty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    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
    ли
    1.34
    ول
    1.10
    り
    0.96
    ور
    0.96
    ના
    0.93
    </h2>
    0.91
     You
    0.90
    м
    0.89
     They
    0.87
     It
    0.86
    POSITIVE LOGITS
    i
    1.11
    in
    1.01
    지
    1.00
    t
    0.97
    تها
    0.95
    ت
    0.91
     пыта
    0.91
     подготов
    0.90
    지와
    0.90
    ي
    0.89
    Activations Density 0.001%

    No Known Activations