© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6927
    Prev
    Next
    INDEX
    Explanations

    words in many languages

    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
    你好
    2.66
     saludos
    2.65
    כם
    2.61
    bleshooting
    2.54
    뿡
    2.52
    мс
    2.51
     شلون
    2.48
    ريض
    2.47
     التواصل
    2.47
     bagay
    2.45
    POSITIVE LOGITS
     eponymous
    1.36
     Twentieth
    1.22
     ehemalige
    1.21
    史上
    1.11
     presidents
    0.96
     depart
    0.95
     Major
    0.94
     mayor
    0.92
     该
    0.89
     Union
    0.88
    Activations Density 0.006%

    No Known Activations