© 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. 64692
    Prev
    Next
    INDEX
    Explanations

    girls and associated words

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

    This neuron activates on occurrences of the capitalized word “Girl” or “Girls” when they appear as part of titles or proper-name headlines.

    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
    visel
    -0.87
     edile
    -0.84
    اران
    -0.82
     pilota
    -0.80
    Attacking
    -0.79
     Contracting
    -0.79
     childrens
    -0.78
    ﻤ
    -0.77
     woman
    -0.76
    ི་
    -0.76
    POSITIVE LOGITS
    sertation
    0.88
     conditioning
    0.77
    ntp
    0.76
    잣
    0.75
     audi
    0.74
    椿
    0.74
     vet
    0.70
    )}(
    0.70
     peaks
    0.69
    ultado
    0.69
    Activations Density 0.011%

    No Known Activations