© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102394
    Prev
    Next
    INDEX
    Explanations

    list manipulation and 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
    ısını
    -0.93
    каун
    -0.82
     berth
    -0.75
    STP
    -0.75
     روسیه
    -0.75
    länd
    -0.72
    ブロ
    -0.69
    OCO
    -0.69
    ierzch
    -0.69
    retario
    -0.69
    POSITIVE LOGITS
     tail
    1.53
     list
    1.46
     Nil
    1.38
    tail
    1.38
    Nil
    1.33
     List
    1.30
     tails
    1.27
    List
    1.20
    tails
    1.19
     Cons
    1.19
    Activations Density 0.046%

    No Known Activations