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. 8454
    Prev
    Next
    INDEX
    Explanations

    code snippets and configurations

    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
     especially
    -1.02
    Especially
    -0.90
     Especially
    -0.79
     Taking
    -0.76
     particularly
    -0.74
     least
    -0.73
    habil
    -0.72
     계획
    -0.72
     Depending
    -0.71
     people
    -0.71
    POSITIVE LOGITS
     façons
    0.88
     infección
    0.79
     eixo
    0.75
     however
    0.75
     échanges
    0.73
    说了
    0.72
    izumi
    0.71
     dismal
    0.71
     appartiennent
    0.71
     segurança
    0.71
    Activations Density 0.050%

    No Known Activations