© 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. 16748
    Prev
    Next
    INDEX
    Explanations

    Patrick, Mexico, Grower

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

    own, native, subsidies, fields, gravity

    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
    UT
    0.39
    ING
    0.38
    RO
    0.38
    Ｔ
    0.38
    И
    0.38
    ALL
    0.37
    ARY
    0.37
    Ρ
    0.36
    IS
    0.36
    OM
    0.36
    POSITIVE LOGITS
     quelqu
    0.35
    ولة
    0.34
     coû
    0.33
     Patrick
    0.33
     کسی
    0.33
     membut
    0.32
     Anwendung
    0.31
     wichtigsten
    0.31
     Grower
    0.31
     iemand
    0.30
    Activations Density 0.008%

    No Known Activations