© 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. 48580
    Prev
    Next
    INDEX
    Explanations

    bride comes to

    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
     bride
    -1.50
    bride
    -1.26
     Bride
    -1.08
     bridegroom
    -1.03
     brides
    -1.03
     bridesmaid
    -0.95
     Brides
    -0.94
     groom
    -0.94
    Bride
    -0.88
    brides
    -0.81
    POSITIVE LOGITS
    ENERGY
    0.94
    qJ
    0.83
    FEBRUARY
    0.80
     Occident
    0.78
     Algunas
    0.78
    junctive
    0.78
     TRO
    0.77
    Todavía
    0.77
    リカ
    0.77
     svoju
    0.77
    Activations Density 0.006%

    No Known Activations