© 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. 22-GEMMASCOPE-RES-131K
    7. 73879
    Prev
    Next
    INDEX
    Explanations

    metal oxide semiconductor

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

    The neuron strongly responds to uncommon, content‐bearing tokens—i.e. technical or domain‐specific keywords—whereas common function words and punctuation register little or no activation.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    :
    -1.20
    ons
    -1.00
    pro
    -0.94
         
    -0.90
    ashvili
    -0.89
     et
    -0.89
    fi
    -0.88
             
    -0.87
     (;;
    -0.86
                     
    -0.84
    POSITIVE LOGITS
     our
    1.19
     that
    1.19
     genieten
    1.08
     jabón
    1.06
    ülerin
    1.01
     éton
    0.97
    yeb
    0.96
     rús
    0.95
    の人生
    0.94
     toalla
    0.94
    Activations Density 0.096%

    No Known Activations