© 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. 31635
    Prev
    Next
    INDEX
    Explanations

    presidential inauguration

    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
     summertime
    -0.80
    казать
    -0.80
     októ
    -0.79
     vakantie
    -0.76
    asil
    -0.74
    OCTOBER
    -0.73
     AWARD
    -0.72
     epist
    -0.71
     commended
    -0.70
    ADL
    -0.70
    POSITIVE LOGITS
     inauguration
    2.25
     Inaug
    1.97
    Inaug
    1.70
     swearing
    1.45
     inaug
    1.45
    inaug
    1.27
     inaugural
    1.26
     oath
    1.20
     inaugu
    1.15
     inaugurated
    1.11
    Activations Density 0.024%

    No Known Activations