© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8272
    Prev
    Next
    INDEX
    Explanations

    geographical entities

    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
    ě
    1.19
    ть
    1.16
    p
    1.14
    the
    1.08
    t
    1.05
    o
    1.05
    е
    1.04
    chell
    1.02
    sho
    1.00
    ється
    0.99
    POSITIVE LOGITS
    为其
    0.88
    ქვენ
    0.85
    ّل
    0.81
    深受
    0.80
     sexes
    0.79
    ក៏
    0.78
     flavours
    0.78
     rearview
    0.78
    정과
    0.77
    ៩
    0.77
    Activations Density 0.115%

    No Known Activations