© 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. 8108
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and business terms

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

    formulas and variables

    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
     проє
    0.79
    <0xC2>
    0.76
    ⁠
    0.75
    ​​​​
    0.66
     XNUMX
    0.64
    ​​
    0.63
     lmao
    0.63
    ​,
    0.63
     ​​​​
    0.61
     reimag
    0.61
    POSITIVE LOGITS
    
    1.60
     
    1.59
     
    1.46
     
    1.38
    
    1.37
    
    1.31
    
    1.30
    
    1.29
     
    1.27
     
    1.26
    Activations Density 0.006%

    No Known Activations