© 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. 99752
    Prev
    Next
    INDEX
    Explanations

    dress code, dressing up

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on occurrences of the token “Dress” (and its inflected forms) wherever it appears in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    嵛
    -0.89
    肚
    -0.84
    omorphisms
    -0.83
     psalm
    -0.82
     clatter
    -0.82
    書いた
    -0.82
     
    -0.82
     самого
    -0.82
    litian
    -0.81
     Upgrades
    -0.81
    POSITIVE LOGITS
     rehearsal
    1.50
     Dress
    1.47
     dress
    1.33
    Dress
    1.26
    👗
    1.24
     code
    1.23
     DRESS
    1.12
    dress
    1.09
     rehearsals
    1.08
     dressing
    1.02
    Activations Density 0.009%

    No Known Activations