© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31244
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and scientific notation

    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_40_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
    лекса
    0.38
     खूब
    0.38
    мно
    0.38
    )=-\
    0.38
     konfl
    0.37
     δικ
    0.37
    炰
    0.37
     menghubungi
    0.36
     Geschichten
    0.35
    }=\
    0.35
    POSITIVE LOGITS
     صغير
    0.36
     forms
    0.35
     léger
    0.35
    nour
    0.34
     Cousin
    0.34
    ငယ်
    0.34
    form
    0.34
     neden
    0.34
    asser
    0.33
     gloves
    0.33
    Activations Density 0.000%

    No Known Activations