© 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. 66906
    Prev
    Next
    INDEX
    Explanations

    way back in

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

    This neuron fires on the colloquial adverb “way” when used as an intensifier (e.g. in phrases like “way back” or “way out”).

    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
     dezelve
    -1.77
     moze
    -1.73
    怍
    -1.68
     parlar
    -1.67
    hasilkan
    -1.64
    ми
    -1.63
    
    -1.63
    
    -1.63
     zoude
    -1.63
     uwe
    -1.63
    POSITIVE LOGITS
    ueves
    1.91
     in
    1.84
    |$.
    1.67
    xFFFFFF
    1.64
    HostException
    1.63
     lidí
    1.63
    </b>
    1.57
    </u>
    1.56
    richlet
    1.56
    ons
    1.53
    Activations Density 0.011%

    No Known Activations