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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60928
    Prev
    Next
    INDEX
    Explanations

    influence of factors

    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
     всіх
    -1.00
    QualifiedName
    -0.92
    もしくは
    -0.85
     necessary
    -0.85
    uristic
    -0.85
    ленная
    -0.85
     potřeb
    -0.85
    ictions
    -0.84
     needed
    -0.84
     відповід
    -0.83
    POSITIVE LOGITS
     location
    1.57
     age
    1.54
     environment
    1.48
     type
    1.45
     size
    1.44
     different
    1.41
     temperature
    1.36
     season
    1.34
     changes
    1.34
     degree
    1.27
    Activations Density 0.334%

    No Known Activations