© 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. 31-GEMMASCOPE-2-RES-262K
    7. 77220
    Prev
    Next
    INDEX
    Explanations

    financial performance and work context

    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
    鎳
    0.46
    Anna
    0.45
     Ко
    0.43
    进口
    0.42
     платфор
    0.42
    ردن
    0.42
     തുറ
    0.42
    לק
    0.41
    вано
    0.40
     महल
    0.40
    POSITIVE LOGITS
     día
    0.43
     Yan
    0.42
     sporadic
    0.42
    /;
    0.41
     dominio
    0.40
    plicial
    0.40
     Ya
    0.40
     Fong
    0.40
     pues
    0.40
    dicts
    0.39
    Activations Density 0.000%

    No Known Activations