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. 65
    Prev
    Next
    INDEX
    Explanations

    bring your own

    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
     informace
    -0.81
     aprendizagem
    -0.78
     закри
    -0.76
     gemacht
    -0.75
     Mme
    -0.73
    pF
    -0.73
    gamon
    -0.72
    wirkungen
    -0.71
     ENJOY
    -0.71
     Dirac
    -0.71
    POSITIVE LOGITS
     bring
    2.42
    Bring
    2.17
    bring
    2.13
     Bring
    2.09
     bringing
    1.97
     own
    1.89
     brought
    1.83
     Bringing
    1.68
     supplied
    1.67
     brings
    1.63
    Activations Density 0.016%

    No Known Activations