© 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. 22-GEMMASCOPE-RES-131K
    7. 16262
    Prev
    Next
    INDEX
    Explanations

    bride and bridal-related concepts

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

    The neuron is primarily activated by occurrences of the word “bride” (and its close morphological variants such as “bridal” or “bridesmaid”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    <em>
    -3.34
    </em>
    -3.25
    <strong>
    -3.00
    f
    -2.70
    n
    -2.67
    d
    -2.67
    ):
    -2.61
     \
    -2.59
    ('
    -2.48
     ‘
    -2.48
    POSITIVE LOGITS
     发型
    2.86
    鹟
    2.80
    鹚
    2.75
    豨
    2.58
     camiset
    2.47
     rése
    2.39
    騭
    2.36
     énergie
    2.33
    
    2.31
    蟊
    2.31
    Activations Density 0.005%

    No Known Activations