© 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. 95252
    Prev
    Next
    INDEX
    Explanations

    homemade or handcrafted goods

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

    homemade and handmade items

    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
    駐車
    0.63
    یا
    0.59
    ार्किक
    0.56
    ковой
    0.54
    大な
    0.52
    最初に
    0.52
    문
    0.51
    ディ
    0.50
    بین
    0.50
     mantan
    0.50
    POSITIVE LOGITS
     Handmade
    0.83
     handmade
    0.82
     homemade
    0.72
    handmade
    0.72
    Homemade
    0.65
     Homemade
    0.64
     изделия
    0.63
    uario
    0.61
     изделий
    0.61
    ان
    0.60
    Activations Density 0.183%

    No Known Activations