© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118946
    Prev
    Next
    INDEX
    Explanations

    Property Tax

    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
     convidados
    -0.83
     equipamentos
    -0.80
    tikal
    -0.79
    cování
    -0.79
    ellingham
    -0.78
     ModelRenderer
    -0.78
    Frederick
    -0.77
    斛
    -0.77
    arrant
    -0.77
     TextInputType
    -0.77
    POSITIVE LOGITS
     final
    1.40
    Bundle
    1.38
     Bundle
    1.18
    final
    1.13
     bundle
    0.89
    最后的
    0.83
     bundles
    0.82
     Bund
    0.80
    FINAL
    0.80
     android
    0.79
    Activations Density 0.003%

    No Known Activations