© 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. 3704
    Prev
    Next
    INDEX
    Explanations

    per followed by units or measures

    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
    2.05
    a
    1.95
    an
    1.88
    ا
    1.57
    ي
    1.55
    ン
    1.50
    ان
    1.48
    া
    1.47
    י
    1.47
    o
    1.45
    POSITIVE LOGITS
    ’
    1.41
     capita
    1.05
     (
    1.01
    Were
    0.98
    were
    0.97
    تها
    0.96
    िक्रमा
    0.93
    drug
    0.86
    sti
    0.84
    drive
    0.84
    Activations Density 0.108%

    No Known Activations