© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3655
    Prev
    Next
    INDEX
    Explanations

    film and quarterback

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

    superlatives followed by nouns

    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
    <unused2121>
    0.52
    Several
    0.50
    In
    0.50
    As
    0.48
    ;
    0.48
    There
    0.48
     several
    0.47
    <u>
    0.47
     some
    0.47
    From
    0.47
    POSITIVE LOGITS
     фильм
    0.87
     фильме
    0.86
     фильма
    0.86
     quarterbacks
    0.84
     ફિલ્મ
    0.83
     कॉमेडी
    0.82
     фильмов
    0.81
    映画
    0.80
     फिल्मों
    0.80
     quarterback
    0.80
    Activations Density 2.472%

    No Known Activations