© 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. 680
    Prev
    Next
    INDEX
    Explanations

    verb-preposition combinations

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

    verb-preposition combinations

    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
     saddhim
    0.31
    पाला
    0.29
     Proficiency
    0.28
     honti
    0.28
    বৃহস্পতিবার
    0.28
    ﻔ
    0.28
     Cited
    0.27
    ᇁ
    0.27
     CODE
    0.27
    ORIES
    0.27
    POSITIVE LOGITS
     freaking
    0.47
     fucking
    0.42
    ‌
    0.36
     bloody
    0.35
     darn
    0.33
     damn
    0.31
     unless
    0.31
    <0xE0>
    0.30
     damned
    0.29
     (&
    0.29
    Activations Density 1.006%

    No Known Activations