© 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. 10-GEMMASCOPE-RES-131K
    7. 65653
    Prev
    Next
    INDEX
    Explanations

    reddy, maxmaxcdn, ASU, bullpen, sve, Middlesbrough

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

    The neuron strongly responds to proper‐name tokens—i.e. named entities such as person surnames or brand/organization 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_10/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
    きち
    -2.69
     he
    -2.67
    𐄁
    -2.58
     verhindert
    -2.38
     gedacht
    -2.31
     denken
    -2.28
    varios
    -2.28
     bezw
    -2.27
    ものに
    -2.27
     juzg
    -2.27
    POSITIVE LOGITS
    ”（
    2.61
     felpa
    2.58
    ２
    2.48
     =
    2.41
    ?"
    2.38
     demean
    2.34
    
    2.27
     blanda
    2.23
    
    2.23
     tableta
    2.22
    Activations Density 0.009%

    No Known Activations