© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99104
    Prev
    Next
    INDEX
    Explanations

    land and terrestrial

    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
     sabes
    -0.75
    adjoint
    -0.73
    いぐるみ
    -0.72
    зите
    -0.69
     objeto
    -0.69
    莹
    -0.68
    古风
    -0.68
     Whitfield
    -0.68
    movq
    -0.68
    userId
    -0.66
    POSITIVE LOGITS
     land
    4.34
     terrestrial
    4.16
    陸
    3.06
     terrestre
    3.00
     terrestres
    2.98
    陆
    2.97
    Land
    2.83
     Terrestrial
    2.75
     Land
    2.70
     overland
    2.67
    Activations Density 0.077%

    No Known Activations