© 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. 8155
    Prev
    Next
    INDEX
    Explanations

    three-phase operation

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

    rape

    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
     syl
    0.40
     cooler
    0.39
    చ్
    0.38
     Hilde
    0.38
    âh
    0.37
    :""
    0.37
     Syl
    0.36
    巖
    0.36
    âne
    0.36
    ڼ
    0.36
    POSITIVE LOGITS
     
    0.79
    
    0.73
    琀
    0.69
    昀
    0.65
    
    0.60
    #######
    0.60
    🠀
    0.57
     
    0.56
    
    0.53
    
    0.50
    Activations Density 0.024%

    No Known Activations