© 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. 3723
    Prev
    Next
    INDEX
    Explanations

    chief followed by officer titles

    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
    т
    1.27
    ت
    1.22
    ม
    1.20
    การ
    1.17
    지
    1.15
    ר
    1.14
     as
    1.12
    ת
    1.10
    ى
    1.07
    त
    1.05
    POSITIVE LOGITS
    in
    1.20
    ong
    1.12
    uksen
    1.08
    ’.”
    1.00
    kých
    0.98
    urer
    0.95
     in
    0.93
     heralded
    0.93
    ła
    0.91
    ování
    0.90
    Activations Density 0.002%

    No Known Activations