© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6773
    Prev
    Next
    INDEX
    Explanations

    verb + preposition + adverb

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

    trained on

    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
    ወሰ
    0.43
    otra
    0.42
    但我
    0.42
     نحو
    0.42
     rendu
    0.40
    垍
    0.40
    рки
    0.39
     लिखेंगे
    0.38
    Wiley
    0.38
    旯
    0.38
    POSITIVE LOGITS
     orderly
    0.46
     correspondingly
    0.45
     definitely
    0.42
     stably
    0.42
     vitally
    0.42
     effectually
    0.42
     tiế
    0.40
    ДИ
    0.40
     seriously
    0.39
     actually
    0.39
    Activations Density 0.043%

    No Known Activations