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. 8366
    Prev
    Next
    INDEX
    Explanations

    react import statements

    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
     this
    -0.92
     København
    -0.88
     because
    -0.87
     before
    -0.86
     in
    -0.86
     as
    -0.85
     This
    -0.84
     during
    -0.81
     one
    -0.80
     two
    -0.79
    POSITIVE LOGITS
     styled
    0.96
     mascota
    0.90
     incred
    0.90
     trám
    0.88
    BarStyle
    0.87
    离开
    0.86
     wiele
    0.86
     errores
    0.84
    让她
    0.83
    𓐍
    0.82
    Activations Density 0.003%

    No Known Activations