© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103453
    Prev
    Next
    INDEX
    Explanations

    artistic subjects and still life

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

    The neuron fires on phrases that introduce examples or enumerate items (e.g. “and a …,” “along with … such as …”).

    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
     Mahat
    -0.90
    ּוֹ
    -0.85
     Dann
    -0.78
    🎄
    -0.72
    iczny
    -0.71
    電子
    -0.71
     Entreprises
    -0.71
    ֶּ
    -0.71
     trilha
    -0.70
    Illustrated
    -0.69
    POSITIVE LOGITS
     still
    2.14
    Still
    2.06
     Still
    1.90
    still
    1.88
     нат
    1.69
     STILL
    1.59
    STILL
    1.51
     fruit
    1.41
     inanimate
    1.24
     ainda
    1.19
    Activations Density 0.016%

    No Known Activations