© 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. 7280
    Prev
    Next
    INDEX
    Explanations

    list items or labels

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

    list item markers a)

    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
    لاح
    0.41
     asiento
    0.41
    cially
    0.41
    স
    0.41
    រក
    0.40
    މ
    0.40
    فكير
    0.40
     advert
    0.39
    އ
    0.39
    bonded
    0.38
    POSITIVE LOGITS
     priori
    0.91
    éreo
    0.82
     partir
    0.80
     posteriori
    0.79
    
    0.77
     través
    0.72
    rizona
    0.71
     partire
    0.71
    ishwarya
    0.70
     menudo
    0.70
    Activations Density 0.036%

    No Known Activations