© 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. 90188
    Prev
    Next
    INDEX
    Explanations

    made suitable

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

    This neuron lights up on detailed product‐description or marketing text listing features, specifications, and selling points.

    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
    tization
    -1.45
     colorful
    -1.34
    customized
    -1.33
     specialized
    -1.32
     organized
    -1.30
     flavor
    -1.30
     analyzed
    -1.29
     neighborhood
    -1.23
     flavors
    -1.23
     neighborhoods
    -1.20
    POSITIVE LOGITS
     whilst
    1.85
    Whilst
    1.60
     Whilst
    1.47
     UK
    1.25
     £
    1.16
     Corée
    1.11
    Σε
    1.11
     specialist
    1.11
     (£
    1.09
    均
    1.08
    Activations Density 0.178%

    No Known Activations