© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 842
    Prev
    Next
    INDEX
    Explanations

    foreign language examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    处于
    0.62
     Dentistry
    0.56
     wasn
    0.54
    the
    0.53
     the
    0.53
    0.52
     someone
    0.52
     数据
    0.50
    你
    0.50
     they
    0.49
    POSITIVE LOGITS
     adicional
    1.06
     importantes
    0.96
     importante
    0.94
     específicas
    0.94
     adicionales
    0.92
     específica
    0.90
     importants
    0.89
     filosóf
    0.89
     inesper
    0.89
     empresarial
    0.88
    Activations Density 0.325%

    No Known Activations