© 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. 14263
    Prev
    Next
    INDEX
    Explanations

    west or western

    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
    ל
    1.33
    an
    1.23
    ler
    1.12
    ם
    1.03
    т
    1.02
    ه
    1.00
    р
    1.00
    َ
    1.00
    ل
    0.93
     to
    0.93
    POSITIVE LOGITS
    西
    1.18
    WEST
    1.13
     पश्चिम
    1.10
     WEST
    1.08
    West
    1.07
     West
    1.01
     west
    1.00
     Tây
    0.99
     western
    0.98
     westward
    0.97
    Activations Density 0.010%

    No Known Activations