© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17342
    Prev
    Next
    INDEX
    Explanations

    list items numbered or lettered

    np_acts-logits-general · gemini-2.5-flash-lite

    fill in the blank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
         
    0.53
     ½
    0.49
     --
    0.49
     ¼
    0.48
    please
    0.47
     ¾
    0.46
    Please
    0.45
          
    0.45
     Ay
    0.45
    find
    0.44
    POSITIVE LOGITS
     reasoning
    0.55
    Exercises
    0.51
     Reasoning
    0.49
     SPORTS
    0.47
     CONCEPT
    0.47
     MAKING
    0.47
     Exercises
    0.46
     පේශ
    0.46
    CONCEPT
    0.45
    鿷
    0.44
    Activations Density 0.011%

    No Known Activations