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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10841
    Prev
    Next
    INDEX
    Explanations

    set operations and data structures

    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
    哽
    0.46
     servidor
    0.45
     горя
    0.43
     وحدة
    0.43
     шка
    0.42
    inizi
    0.42
    ukebox
    0.42
    गर
    0.41
     यंत्र
    0.41
    伤
    0.41
    POSITIVE LOGITS
     HashSet
    1.13
    HashSet
    1.04
     TreeSet
    0.77
     StringSet
    0.75
     subset
    0.75
     Subset
    0.74
    subset
    0.71
     subsets
    0.71
    集合
    0.69
    =\{
    0.68
    Activations Density 0.071%

    No Known Activations