© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90985
    Prev
    Next
    INDEX
    Explanations

    natural landscapes and environments

    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
    uebas
    -0.93
    nagel
    -0.91
     extremely
    -0.91
     incredibly
    -0.85
     blatant
    -0.85
     insanely
    -0.84
    씨
    -0.83
    weile
    -0.81
     distinctive
    -0.81
    قيقي
    -0.80
    POSITIVE LOGITS
     areas
    1.81
     zone
    1.73
     area
    1.45
     zones
    1.27
     environment
    1.23
     terrain
    1.23
     ecosystems
    1.20
     environments
    1.16
     regions
    1.06
     lands
    1.05
    Activations Density 0.053%

    No Known Activations