© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 11192
    Prev
    Next
    INDEX
    Explanations

    polar bears and penguins

    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_31_width_65k_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
    苎
    0.54
    raintree
    0.51
    财产
    0.45
    农
    0.45
    bedkar
    0.45
    蛊
    0.44
    农村
    0.44
    荥
    0.44
    豇
    0.44
    嫘
    0.44
    POSITIVE LOGITS
     Arctic
    1.42
     arctic
    1.33
    Arctic
    1.30
     Antarctic
    1.24
     ice
    1.23
     Antarctica
    1.23
     tundra
    1.19
     Inuit
    1.16
     Ice
    1.09
     snow
    1.08
    Activations Density 0.066%

    No Known Activations