© 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. 21447
    Prev
    Next
    INDEX
    Explanations

    thank you for

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

    The neuron activates on expressions of gratitude (e.g. “thank,” “thanks,” “thank you”).

    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
     refroid
    -2.02
    
    -1.74
     dénon
    -1.69
     véhic
    -1.59
     précip
    -1.55
     薬局
    -1.52
    Зно
    -1.47
     ursprüng
    -1.47
     eigentliche
    -1.47
    Sprache
    -1.46
    POSITIVE LOGITS
     to
    2.39
     in
    2.20
     all
    1.50
     —
    1.48
    чені
    1.46
     are
    1.45
     despite
    1.41
     „
    1.40
     continue
    1.35
     did
    1.34
    Activations Density 0.009%

    No Known Activations