© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8448
    Prev
    Next
    INDEX
    Explanations

    order of operations expressions

    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_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
     HDTV
    0.45
     exhibit
    0.41
     exhibiting
    0.39
     exhib
    0.38
     pair
    0.37
     Buildings
    0.37
     домов
    0.37
    廃
    0.36
     Moto
    0.36
     Exhibits
    0.36
    POSITIVE LOGITS
     prioritization
    0.53
     først
    0.52
     priorit
    0.50
     prioritized
    0.49
    優先
    0.49
     prioridad
    0.49
     перво
    0.48
    优先级
    0.48
     prioritize
    0.47
     prioritizing
    0.47
    Activations Density 0.199%

    No Known Activations