© 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. 117995
    Prev
    Next
    INDEX
    Explanations

    forests and landscapes

    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
    ⡟
    -0.92
    zygous
    -0.85
    lahraga
    -0.80
    inatal
    -0.79
     CONTACT
    -0.79
    NOSTIC
    -0.77
    ieniu
    -0.77
    oczes
    -0.76
    ولوژی
    -0.76
     PDI
    -0.75
    POSITIVE LOGITS
     livelihoods
    1.19
     livelihood
    1.12
     buffer
    1.08
     forest
    1.07
     conservation
    1.01
     дре
    0.98
     Payments
    0.94
     villagers
    0.93
     landscape
    0.93
    Conservation
    0.90
    Activations Density 0.019%

    No Known Activations