© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5356
    Prev
    Next
    INDEX
    Explanations

    contrast or qualification

    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_12_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
     quindi
    1.59
     therefore
    1.43
     /
    1.31
    aliya
    1.27
     portanto
    1.26
    /,
    1.23
     possibility
    1.21
     '#
    1.21
     donc
    1.19
     /.
    1.17
    POSITIVE LOGITS
    却没有
    2.94
    却是
    2.83
    実際
    2.56
     nevertheless
    2.52
    并未
    2.51
     nonetheless
    2.49
    一方で
    2.49
    并非
    2.45
    仍
    2.41
    却
    2.36
    Activations Density 0.618%

    No Known Activations