© 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. 44721
    Prev
    Next
    INDEX
    Explanations

    mail as, located on

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

    specific command

    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
    黯
    0.54
    กีฬา
    0.52
    綜
    0.46
    interesse
    0.45
    企业家
    0.44
     Panchayat
    0.43
    вате
    0.42
     sentimento
    0.42
     تلاش
    0.41
    ArchivePath
    0.41
    POSITIVE LOGITS
     চাক
    0.53
     ଯ
    0.49
     răng
    0.47
     choroby
    0.47
     контроли
    0.46
    က်
    0.46
    ုန်း
    0.46
     najwięks
    0.46
    ohm
    0.45
     zmiany
    0.45
    Activations Density 0.001%

    No Known Activations