Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7766
    Prev
    Next
    INDEX
    Explanations

    housing market transactions

    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
     retrovisor
    -0.78
     feiner
    -0.75
     tecido
    -0.75
     věci
    -0.74
     deseado
    -0.73
     procedimientos
    -0.72
     pomá
    -0.72
     orgánico
    -0.71
    benhavn
    -0.71
     instincts
    -0.71
    POSITIVE LOGITS
    buying
    1.27
     buying
    1.27
    buyers
    1.24
    buyer
    1.23
     buyers
    1.18
     purchase
    1.14
     buyer
    1.13
     sale
    1.11
    Buying
    1.05
     size
    1.04
    Activations Density 0.023%

    No Known Activations