© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 513
    Prev
    Next
    INDEX
    Explanations

    cables and electrical systems

    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
     Olympics
    -0.78
     ресторан
    -0.77
     Minnesota
    -0.74
    station
    -0.73
     Bob
    -0.73
     Bioaccumulative
    -0.71
     Бал
    -0.71
     STATION
    -0.71
     Salt
    -0.70
     Puerto
    -0.69
    POSITIVE LOGITS
    fuse
    0.81
     Ihm
    0.76
     crossorigin
    0.74
     loadings
    0.71
     hängt
    0.71
    })_{
    0.71
    ėk
    0.71
     washable
    0.71
     domestic
    0.70
    kao
    0.70
    Activations Density 0.005%

    No Known Activations