© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2820
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find mentions of hair (and hair‐related styling or product details).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    跛
    0.60
     Jdbc
    0.57
    ពិ
    0.53
     жер
    0.53
     কলেরা
    0.53
     fasilitas
    0.52
     Isometric
    0.52
    🍶
    0.52
    XM
    0.52
     Stab
    0.52
    POSITIVE LOGITS
     hair
    3.00
     Hair
    2.89
    Hair
    2.80
    hair
    2.66
     HAIR
    2.64
     hairstyle
    2.58
     haird
    2.56
     hairc
    2.55
     hairst
    2.50
     hairstyles
    2.45
    Activations Density 0.473%

    No Known Activations