© 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. 12-GEMMASCOPE-2-RES-16K
    7. 12541
    Prev
    Next
    INDEX
    Explanations

    **Detecting multilingual input end**

    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_12_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
     to
    1.07
     as
    0.96
     S
    0.94
     pretzels
    0.89
     in
    0.89
     calipers
    0.89
     or
    0.87
     ago
    0.87
     up
    0.87
     was
    0.86
    POSITIVE LOGITS
    ع
    1.19
    ો
    1.02
    ă
    1.00
    ább
    0.99
    owały
    0.93
    ilidad
    0.93
    란드
    0.93
    র
    0.92
     Información
    0.89
    ěji
    0.88
    Activations Density 0.319%

    No Known Activations