© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63390
    Prev
    Next
    INDEX
    Explanations

    set and hashset data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImmutableList
    -0.81
    ApJ
    -0.81
    aimerais
    -0.79
    Lists
    -0.79
     lists
    -0.77
     Lists
    -0.75
     externos
    -0.74
    emptyList
    -0.74
     скла
    -0.73
    áso
    -0.73
    POSITIVE LOGITS
     HashSet
    1.70
    HashSet
    1.35
     resultSet
    1.14
     subset
    1.07
    TreeSet
    1.04
     مجموعة
    1.03
     membership
    1.01
    FieldSet
    0.98
     Sets
    0.98
     TreeSet
    0.93
    Activations Density 0.020%

    No Known Activations