© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 161298
    Prev
    Next
    INDEX
    Explanations

    phrasal verb completions

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

    Wes Anderson

    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_31_width_262k_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
    基地
    0.52
     hospitales
    0.49
    ंजनों
    0.48
    мін
    0.47
    ковий
    0.47
     کھیل
    0.46
     urbano
    0.46
    逢
    0.45
    village
    0.45
    лина
    0.45
    POSITIVE LOGITS
     illust
    0.50
     пока
    0.50
     bip
    0.49
    zat
    0.46
     Illust
    0.46
     brach
    0.46
     рассчита
    0.46
     च
    0.46
     close
    0.46
     λ
    0.46
    Activations Density 0.000%

    No Known Activations