© 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. 16-GEMMASCOPE-2-RES-262K
    7. 749
    Prev
    Next
    INDEX
    Explanations

    evasion and circumvention

    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_16_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
     I
    0.90
    t
    0.83
    ن
    0.76
    n
    0.76
    re
    0.75
    น้อง
    0.66
    𝐢
    0.66
    啉
    0.65
    it
    0.64
    و
    0.64
    POSITIVE LOGITS
    д
    0.86
     دلیل
    0.77
    ール
    0.77
     şekilde
    0.71
    ༦
    0.71
    Università
    0.70
    šenje
    0.70
    Université
    0.69
    л
    0.67
    ف
    0.67
    Activations Density 0.034%

    No Known Activations