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. 53-GEMMASCOPE-2-RES-262K
    4. 14016
    Prev
    Next
    INDEX
    Explanations

    official documentation and services

    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_53_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
    Details
    0.34
    了
    0.32
      
    0.32
    https
    0.31
     sidel
    0.30
     синд
    0.30
     outweigh
    0.30
     with
    0.29
     largely
    0.29
     Primarily
    0.29
    POSITIVE LOGITS
    님의
    0.37
     által
    0.36
    ရဲ့
    0.34
    嘅
    0.34
    ның
    0.34
     tarafından
    0.34
     কর্তৃক
    0.33
    official
    0.33
     official
    0.33
     তরফে
    0.33
    Activations Density 0.041%

    No Known Activations