© 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. 58872
    Prev
    Next
    INDEX
    Explanations

    commencement speech or address

    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
    inas
    -0.80
     Glasgow
    -0.78
    phos
    -0.73
     followers
    -0.73
     kos
    -0.69
    reducer
    -0.69
     bleached
    -0.69
    spesies
    -0.68
    Serves
    -0.67
    醯
    -0.67
    POSITIVE LOGITS
     commencement
    1.09
     invocation
    1.09
     medalist
    0.91
     Invocation
    0.88
     eu
    0.82
     val
    0.82
     tying
    0.81
    eu
    0.81
     featured
    0.80
     Commencement
    0.80
    Activations Density 0.027%

    No Known Activations