© 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. 6437
    Prev
    Next
    INDEX
    Explanations

    pronouns preceding verbs or nouns

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

    Emoji and foreign characters

    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
     Recht
    0.50
    峮
    0.50
     yanlı
    0.49
    ordelen
    0.49
    unzione
    0.49
    ianum
    0.48
     견
    0.47
     অঙ্গ
    0.47
     DENUMIRE
    0.47
     ljubav
    0.47
    POSITIVE LOGITS
    ك
    0.57
    ل
    0.54
    جور
    0.49
    Google
    0.46
    シェ
    0.46
    今回
    0.46
    私たち
    0.46
    NY
    0.44
     You
    0.44
    太平洋
    0.43
    Activations Density 0.000%

    No Known Activations