© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7756
    Prev
    Next
    INDEX
    Explanations

    resource utilization and management

    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_16k_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
    i
    3.49
    ی
    3.44
    e
    3.43
    s
    2.78
    특별시
    2.60
    いく
    2.50
    m
    2.37
    йга
    2.36
    یە
    2.36
    n
    2.35
    POSITIVE LOGITS
    𝘻
    2.92
    𝘭
    2.73
    蠣
    2.73
    AsStream
    2.73
    𝐳
    2.66
    𝘳
    2.56
    鵡
    2.54
    কেন্ড
    2.49
     doGet
    2.49
    𝘴
    2.41
    Activations Density 0.499%

    No Known Activations