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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99654
    Prev
    Next
    INDEX
    Explanations

    in followed by types of rooms

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

    The neuron fires strongly on occurrences of the phrase “walk-in.”

    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
    {
    -2.08
     tika
    -1.59
     \
    -1.52
     gider
    -1.52
    ction
    -1.39
     Suomessa
    -1.38
    ↵
    -1.38
     nye
    -1.37
    стям
    -1.35
    
    -1.34
    POSITIVE LOGITS
     These
    1.66
    𓋼
    1.64
    𝘢
    1.58
     besucht
    1.56
    获奖
    1.53
     diterapkan
    1.50
    锛
    1.48
     давления
    1.47
     heridas
    1.47
     aftermath
    1.47
    Activations Density 0.005%

    No Known Activations