© 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. 3422
    Prev
    Next
    INDEX
    Explanations

    knew he had to

    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
    telek
    1.22
    ALLOC
    1.21
    UTICAL
    1.21
    =\"
    1.18
    chließlich
    1.17
    ibraries
    1.17
    ECUTIVE
    1.15
    apek
    1.15
    hörigen
    1.14
    ielleicht
    1.14
    POSITIVE LOGITS
     veilig
    1.36
    錯
    1.32
    错了
    1.31
    風險
    1.27
     risk
    1.27
     Safety
    1.27
    风险
    1.25
    ปลอดภัย
    1.25
     Caution
    1.24
     safety
    1.22
    Activations Density 0.109%

    No Known Activations