Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7963
    Prev
    Next
    INDEX
    Explanations

    TJ, Taj, Tij, TJs (names, initials, abbreviations)

    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
    nenie
    -0.87
    ivka
    -0.75
     MARIA
    -0.75
    isement
    -0.72
    dova
    -0.71
     markings
    -0.69
    acija
    -0.68
    MediaType
    -0.68
    ライン
    -0.68
    embeddings
    -0.67
    POSITIVE LOGITS
     business
    0.77
     vuotta
    0.77
     Lá
    0.76
     TJ
    0.75
     Così
    0.73
     烟
    0.72
     Max
    0.71
    Oe
    0.70
    Calgary
    0.70
    cí
    0.69
    Activations Density 0.020%

    No Known Activations