© 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. 114995
    Prev
    Next
    INDEX
    Explanations

    organizations and global terms

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

    grief, wolf, tolerance, remove, heights, encapsulates

    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
    with
    0.57
    stile
    0.54
    ton
    0.51
    p
    0.50
    less
    0.49
    til
    0.47
    ndal
    0.47
    s
    0.47
    rit
    0.47
    sru
    0.46
    POSITIVE LOGITS
     موږ
    0.54
    ناوی
    0.50
     ادار
    0.48
     desarrolló
    0.48
    部署
    0.46
    早就
    0.45
    顧問
    0.45
    輸出
    0.44
     متعلق
    0.44
     compagnies
    0.43
    Activations Density 0.003%

    No Known Activations