© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85629
    Prev
    Next
    INDEX
    Explanations

    never

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

    The neuron activates on negative‐polarity words—especially “never” and other terms expressing inability or negation.

    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
     lenge
    -1.79
     lili
    -1.71
    茈
    -1.68
     nini
    -1.66
     kila
    -1.61
    衕
    -1.59
    
    -1.59
     goi
    -1.59
     sement
    -1.58
    Уже
    -1.58
    POSITIVE LOGITS
     NEVER
    2.16
     a
    1.91
     about
    1.81
     two
    1.80
     never
    1.78
     or
    1.73
     that
    1.73
     Never
    1.70
    </i>
    1.69
     should
    1.63
    Activations Density 0.100%

    No Known Activations