© 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. 2737
    Prev
    Next
    INDEX
    Explanations

    lip products or parts

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

    The neuron fires on mentions of lip cosmetics—especially “lip” or “lips” in product names or descriptions.

    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
     پوست
    -0.79
    lamó
    -0.77
     глаз
    -0.76
     fp
    -0.76
     cleaned
    -0.76
    smc
    -0.75
     étab
    -0.75
     skin
    -0.74
    dns
    -0.74
    sief
    -0.73
    POSITIVE LOGITS
     lips
    1.83
     lip
    1.73
     Lip
    1.59
    Lip
    1.47
    唇
    1.45
     Lippen
    1.39
     Lips
    1.38
     gloss
    1.31
    Lips
    1.27
     ลิ
    1.27
    Activations Density 0.007%

    No Known Activations