© 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. 1382
    Prev
    Next
    INDEX
    Explanations

    censorship

    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
    ant
    0.88
     infirm
    0.83
    و
    0.75
    ق
    0.75
    เป็น
    0.75
    یه
    0.73
     anemia
    0.71
    ่ง
    0.70
    ‌ای
    0.70
     (
    0.69
    POSITIVE LOGITS
    。
    0.95
     Cens
    0.82
     censored
    0.79
    8
    0.78
    يد
    0.76
    وفي
    0.75
     censoring
    0.74
    '।
    0.73
    2
    0.73
     سلي
    0.72
    Activations Density 0.005%

    No Known Activations