© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55650
    Prev
    Next
    INDEX
    Explanations

    multilingual considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     пе
    0.47
     мг
    0.47
    orderInCategory
    0.47
    更换
    0.47
    𝙙
    0.45
     полуо
    0.44
     गैस
    0.44
     дро
    0.44
     пера
    0.44
    itech
    0.44
    POSITIVE LOGITS
    คล
    0.47
    ewnątrz
    0.41
    هم
    0.40
     unavoid
    0.38
     autonomia
    0.38
     Club
    0.38
    |^{
    0.38
    ဖြစ်
    0.38
    <start_of_image>
    0.38
     Byzant
    0.37
    Activations Density 0.007%

    No Known Activations