© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7326
    Prev
    Next
    INDEX
    Explanations

    custom tailored, centered on

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

    fractions of teaspoons

    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
     accomod
    1.16
     occured
    1.00
     seperate
    0.96
     tambien
    0.96
     recieve
    0.95
     occuring
    0.95
    〜
    0.92
     inital
    0.92
     ''
    0.90
     recieved
    0.90
    POSITIVE LOGITS
    
    1.71
    
    1.63
     
    1.48
     ¾
    1.48
     ½
    1.46
     ¼
    1.39
    ‟
    1.39
    
    1.30
    
    1.30
    
    1.27
    Activations Density 0.229%

    No Known Activations