© 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. 31199
    Prev
    Next
    INDEX
    Explanations

    wheel lug nuts

    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
    CGRect
    -0.78
    uesia
    -0.72
    PageFactory
    -0.71
    SharedModule
    -0.70
     Dib
    -0.69
     brisket
    -0.68
    Haar
    -0.68
    égories
    -0.67
     machete
    -0.67
    ला
    -0.66
    POSITIVE LOGITS
     lug
    1.76
     lugs
    1.43
    lug
    1.28
     Lug
    1.24
    Lug
    1.15
     hub
    1.13
     wheel
    1.05
     nuts
    1.05
     conical
    0.93
    nuts
    0.93
    Activations Density 0.014%

    No Known Activations