© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 809
    Prev
    Next
    INDEX
    Explanations

    job titles and professional roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    وزه
    1.30
    printStackTrace
    1.27
     bellow
    1.25
    看出
    1.24
     arou
    1.24
    荼
    1.24
     eût
    1.23
    槍
    1.22
     unamb
    1.22
    鬧
    1.20
    POSITIVE LOGITS
     presso
    1.27
     specializing
    1.19
     сосредото
    1.16
     tại
    1.15
    ǀ
    1.15
     adjunct
    1.11
    专注于
    1.11
     Adj
    1.09
    atted
    1.09
     Specialist
    1.08
    Activations Density 1.040%

    No Known Activations