© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83384
    Prev
    Next
    INDEX
    Explanations

    tractor and related machinery

    np_acts-logits-general · gemini-2.5-flash-lite

    compact tractors and heavy equipment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    冤
    0.50
     paranoid
    0.48
     conson
    0.47
     انتخابات
    0.47
     clueless
    0.47
     politico
    0.45
    开车
    0.45
     सियासी
    0.45
     eleições
    0.44
    riminal
    0.44
    POSITIVE LOGITS
     tractor
    1.17
     tractors
    1.14
     Tractor
    1.10
    tractor
    0.92
    🚜
    0.86
     Deere
    0.84
     ट्रैक्टर
    0.82
     трак
    0.82
     mower
    0.81
     Caterpillar
    0.81
    Activations Density 0.114%

    No Known Activations