© 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. 2561
    Prev
    Next
    INDEX
    Explanations

    write essay prompts

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

    fight after ://

    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
    뀌
    0.42
    떠
    0.40
     Kiya
    0.40
    醐
    0.39
    𝗬
    0.39
    പക്ഷം
    0.39
     ABSORBED
    0.39
     संबंध
    0.38
    absorption
    0.38
    
    0.38
    POSITIVE LOGITS
    Popular
    0.66
     AU
    0.62
     Popular
    0.60
     popular
    0.58
    Cheap
    0.58
     Cheap
    0.57
     Au
    0.56
     au
    0.55
    popular
    0.55
    AU
    0.54
    Activations Density 0.011%

    No Known Activations