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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102536
    Prev
    Next
    INDEX
    Explanations

    tires and tire brands

    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
     DCE
    -0.79
    ството
    -0.79
    垣
    -0.79
    UnknownFields
    -0.77
    '>"
    -0.73
    ()"
    -0.71
     طب
    -0.70
     Railways
    -0.70
     EDM
    -0.69
    じた
    -0.68
    POSITIVE LOGITS
     tires
    2.14
     Brid
    1.91
     Michelin
    1.82
     Firestone
    1.79
     Goodyear
    1.69
     tire
    1.68
     Pirelli
    1.60
     tyres
    1.53
    Brid
    1.47
     Dunlop
    1.44
    Activations Density 0.022%

    No Known Activations