© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11122
    Prev
    Next
    INDEX
    Explanations

    garage and basement structures

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

    garage and basement locations

    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_40_width_16k_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
     Fields
    0.39
    FIELDS
    0.38
    Fields
    0.38
     Spec
    0.37
     fields
    0.36
     zet
    0.36
    迂
    0.36
     fielded
    0.35
    氈
    0.35
     FIELDS
    0.35
    POSITIVE LOGITS
     garage
    1.92
     Garage
    1.80
    Garage
    1.79
    garage
    1.78
     гара
    1.72
     garages
    1.71
     garagem
    1.46
     carport
    1.21
     gara
    1.09
     shed
    1.00
    Activations Density 0.306%

    No Known Activations