© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 54038
    Prev
    Next
    INDEX
    Explanations

    artists painting faces

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

    The neuron fires on occurrences of “face painter” (and related service‐ad words around hiring face‐painting services).

    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
     Semoga
    -0.80
    anshi
    -0.80
     Leuven
    -0.78
     Mungkin
    -0.73
    мужские
    -0.72
     Semua
    -0.71
     Meskipun
    -0.71
    ناعة
    -0.69
     GAY
    -0.69
     Sebelum
    -0.69
    POSITIVE LOGITS
     face
    2.53
     Face
    2.09
    face
    1.94
     painted
    1.90
     paint
    1.84
    Face
    1.80
    paint
    1.68
     paints
    1.60
     painting
    1.54
    painted
    1.53
    Activations Density 0.015%

    No Known Activations