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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8047
    Prev
    Next
    INDEX
    Explanations

    workhorse

    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
    tersebut
    -0.83
    choenen
    -0.81
     مشين
    -0.77
    mengg
    -0.76
    什么事
    -0.73
    assertRaises
    -0.71
    tungen
    -0.71
    ophageal
    -0.71
    seekers
    -0.71
    ᴢ
    -0.71
    POSITIVE LOGITS
     work
    2.78
    horse
    2.52
    Work
    2.41
     Work
    2.28
     horse
    2.22
    work
    2.09
     WORK
    1.85
    WORK
    1.84
    horses
    1.73
     horses
    1.71
    Activations Density 0.057%

    No Known Activations