© 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. 142027
    Prev
    Next
    INDEX
    Explanations

    conclusions and dependencies

    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
    v
    1.45
    យើង
    1.02
    其他
    0.98
    p
    0.96
    ل
    0.95
    ج
    0.92
    리
    0.86
    ve
    0.82
    ল
    0.80
    z
    0.79
    POSITIVE LOGITS
    。
    1.01
    ों
    0.98
    ।
    0.97
    1
    0.96
     Batavia
    0.86
     I
    0.85
    ς
    0.80
    ση
    0.79
    ката
    0.79
    каз
    0.79
    Activations Density 0.005%

    No Known Activations