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. 8320
    Prev
    Next
    INDEX
    Explanations

    Go test functions

    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
     männis
    -0.82
     méret
    -0.77
    меты
    -0.76
     چگونه
    -0.75
     jusqu
    -0.73
    რო
    -0.73
     kardashian
    -0.71
     barne
    -0.71
    Epoxy
    -0.71
     chỉ
    -0.71
    POSITIVE LOGITS
    type
    1.30
     type
    1.23
     tests
    1.15
     examples
    1.12
    tests
    1.07
     want
    0.96
     cases
    0.95
     culturally
    0.90
     for
    0.90
    cases
    0.89
    Activations Density 0.005%

    No Known Activations