© 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. 2579
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

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

    positive descriptions of quality or service

    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
     egregious
    0.52
     appetizer
    0.48
     upscale
    0.48
     headquartered
    0.45
     hipster
    0.43
    罹
    0.43
     sorta
    0.43
     splurge
    0.43
     folks
    0.42
    壹
    0.42
    POSITIVE LOGITS
     fab
    0.79
     brill
    0.74
     Brilliant
    0.73
    Fab
    0.69
     brilliant
    0.68
    Lovely
    0.67
    lovely
    0.64
     Fab
    0.64
     Lovely
    0.62
     lovely
    0.61
    Activations Density 0.120%

    No Known Activations