Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 1587
    Prev
    Next
    INDEX
    Explanations

    physical state and texture

    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_40_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
     финансо
    0.55
     منهج
    0.54
    权力
    0.54
     नैतिक
    0.53
    调度
    0.53
    驷
    0.50
     سیاست
    0.49
     финанси
    0.49
    ခဲ့
    0.48
    鍙
    0.48
    POSITIVE LOGITS
     texture
    1.39
     textura
    1.16
    texture
    1.15
     glistening
    1.13
     Texture
    1.05
     translucent
    1.03
     textures
    1.02
     velvety
    0.99
     creamy
    0.98
    Texture
    0.98
    Activations Density 0.111%

    No Known Activations