© 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-262K
    7. 53762
    Prev
    Next
    INDEX
    Explanations

    word construction and transformations

    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
    not
    0.45
     модерни
    0.44
    hotite
    0.44
    г
    0.43
    राज
    0.42
    グル
    0.41
    ט
    0.41
    ٹ
    0.41
     எடு
    0.40
     மொழ
    0.40
    POSITIVE LOGITS
    ه‌ها
    0.47
     indexOf
    0.45
    ্লি
    0.45
    匹配
    0.44
    Mappings
    0.44
     fondamentali
    0.44
     clustering
    0.43
     mappings
    0.42
     clipart
    0.42
     habitudes
    0.42
    Activations Density 0.002%

    No Known Activations