© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10969
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by descriptor

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

    your friend

    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_40_width_16k_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
    Mathemat
    0.39
     முன்னணி
    0.38
     catal
    0.38
    トン
    0.38
    磊
    0.36
     நடவடிக்கைகள்
    0.35
     নিজেকে
    0.35
    এসই
    0.35
    龐
    0.35
    $&$-
    0.35
    POSITIVE LOGITS
     oyster
    0.57
     lifeline
    0.52
     masterpiece
    0.49
     speciality
    0.47
     prioridad
    0.47
     Nem
    0.46
     specialty
    0.46
     nemesis
    0.46
     undo
    0.46
     prerogative
    0.46
    Activations Density 0.259%

    No Known Activations