© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 680
    Prev
    Next
    INDEX
    Explanations

    assertion status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    𝙢
    1.66
    𝗺
    1.56
    athor
    1.47
    deleted
    1.39
     dues
    1.35
    ittarius
    1.35
     серд
    1.35
    debt
    1.33
    Debt
    1.31
    ɱ
    1.31
    POSITIVE LOGITS
    imonials
    1.98
     nghiệm
    1.91
     tests
    1.91
     junit
    1.86
     vizsgál
    1.86
    驗
    1.85
     Tester
    1.83
    测试
    1.83
     tester
    1.82
     测试
    1.79
    Activations Density 0.447%

    No Known Activations