© 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. 107279
    Prev
    Next
    INDEX
    Explanations

    chairs and tables

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

    The neuron fires on enumerated lists of tangible items (e.g. menu offerings or things “to bring,” like blankets and chairs).

    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
     Dict
    -1.02
    ɧ
    -0.86
    BuilderFactory
    -0.72
    }\]
    -0.71
    Fixes
    -0.70
     fost
    -0.69
     dict
    -0.68
     undecided
    -0.68
    seler
    -0.68
     сове
    -0.68
    POSITIVE LOGITS
     chairs
    3.58
     chair
    2.59
     Chairs
    2.53
    chairs
    2.42
    Chairs
    2.36
     CHAIR
    2.11
     sillas
    1.95
    chair
    1.90
     tables
    1.75
     folding
    1.74
    Activations Density 0.019%

    No Known Activations