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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106536
    Prev
    Next
    INDEX
    Explanations

    desert areas

    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
    氧
    -0.76
    Nep
    -0.69
     kendisi
    -0.69
     打
    -0.68
     поток
    -0.68
    endon
    -0.67
     Oba
    -0.66
     Neto
    -0.65
    洞
    -0.64
     加
    -0.63
    POSITIVE LOGITS
    Desert
    1.25
     desert
    1.23
    desert
    1.20
     Desert
    1.20
     camel
    1.02
     Rajasthan
    1.02
     Thar
    0.94
     dune
    0.93
     Jod
    0.92
     camels
    0.92
    Activations Density 0.017%

    No Known Activations