© 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. 8176
    Prev
    Next
    INDEX
    Explanations

    future or personal possession

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

    qualifying adjectives and adverbs

    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
     realizing
    0.39
    墂
    0.38
     Конгрегация
    0.38
    Fot
    0.37
    `-
    0.37
    or
    0.36
    Sic
    0.36
    ache
    0.36
     pref
    0.36
    ”
    0.36
    POSITIVE LOGITS
     putative
    0.63
     razvoj
    0.60
     shadowy
    0.57
     dreary
    0.57
     makeshift
    0.56
     kaleidoscopic
    0.56
     tumultuous
    0.56
     iterative
    0.55
     whimsical
    0.54
     semblance
    0.54
    Activations Density 0.130%

    No Known Activations