© 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. 91910
    Prev
    Next
    INDEX
    Explanations

    brake pad antifriction pistons

    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
    ëlle
    -0.69
     Goat
    -0.68
    oliver
    -0.68
    entras
    -0.68
    切れ
    -0.67
    рѣ
    -0.67
     cockroach
    -0.66
    CONTINUE
    -0.66
    riche
    -0.66
     Mage
    -0.65
    POSITIVE LOGITS
     caliper
    1.90
     calipers
    1.83
     Cali
    1.23
     calli
    1.20
    calli
    1.11
     суп
    1.00
    piston
    0.97
     piston
    0.97
     pistons
    0.96
     cali
    0.96
    Activations Density 0.024%

    No Known Activations