© 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. 34-GEMMASCOPE-RES-131K
    7. 108597
    Prev
    Next
    INDEX
    Explanations

    Stay followed by common phrases

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

    The neuron detects occurrences of the word “stay” (in any case or as part of a compound token).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    prescription
    -0.92
    gawai
    -0.85
     Prevalence
    -0.85
     ساختمان
    -0.83
     동
    -0.81
     gedung
    -0.80
     دارو
    -0.80
     oraș
    -0.78
    techniques
    -0.78
    を経て
    -0.78
    POSITIVE LOGITS
     tuned
    1.55
    cation
    1.25
    Stay
    1.18
    stay
    1.13
     longer
    1.08
     Stay
    1.07
     stay
    1.03
     inexplicable
    1.02
     STAY
    0.97
    ect
    0.89
    Activations Density 0.007%

    No Known Activations