© 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. 32623
    Prev
    Next
    INDEX
    Explanations

    eyeshadow

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

    The neuron flags cosmetic product titles and headings (especially eye-shadow lines and related product names).

    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
     smeared
    -0.78
    ッチン
    -0.73
    vanju
    -0.72
     美容
    -0.72
     inicial
    -0.72
     Anfang
    -0.71
     órganos
    -0.71
    setBold
    -0.71
    inkan
    -0.70
    Sme
    -0.70
    POSITIVE LOGITS
     shadow
    1.60
     shadows
    1.59
     eyeshadow
    1.46
    shadow
    1.25
     Shadow
    1.23
     Shadows
    1.23
    Shadows
    1.20
    Shadow
    1.20
     eye
    1.16
     blush
    1.16
    Activations Density 0.021%

    No Known Activations