© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 48298
    Prev
    Next
    INDEX
    Explanations

    expressing gratitude

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

    The neuron identifies expressions of gratitude—tokens like “thank,” “thanks,” “thankful,” and related forms.

    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
     to
    -1.63
    ).
    -1.57
    秶
    -1.51
    }`
    -1.45
    臜
    -1.43
    t
    -1.41
    ……。
    -1.40
    iyaki
    -1.39
     will
    -1.38
    tischen
    -1.36
    POSITIVE LOGITS
    žití
    1.53
     a
    1.47
     calcetines
    1.40
    ες
    1.39
     Menschheit
    1.38
    itsubishi
    1.36
     honnête
    1.33
     bertanya
    1.31
     écout
    1.31
    ẩ
    1.30
    Activations Density 0.010%

    No Known Activations