© 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. 178864
    Prev
    Next
    INDEX
    Explanations

    scholarship

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

    possessive pronouns + descriptions

    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
    ﮈ
    0.48
    פק
    0.46
     Choice
    0.45
    アシ
    0.45
     Leader
    0.44
     legge
    0.44
     sécrétion
    0.44
     Nested
    0.44
    旂
    0.44
    暾
    0.44
    POSITIVE LOGITS
     outfits
    0.53
     ایک
    0.52
    overwrite
    0.51
     outfit
    0.48
     पैमाने
    0.48
    大量的
    0.48
     ethnographic
    0.47
     &#
    0.47
    िंग
    0.47
    ्
    0.47
    Activations Density 0.000%

    No Known Activations