© 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. 22-GEMMASCOPE-RES-131K
    7. 14398
    Prev
    Next
    INDEX
    Explanations

    greetinggreeting followed by punctuationgreeting initiating discourse

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

    The neuron activates on informal greetings and farewells like “hi” and “bye.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    <td>
    -2.91
    .’
    -2.67
    m
    -2.66
    “
    -2.66
    .“
    -2.66
    ↵↵
    -2.50
    —“
    -2.41
     of
    -2.36
     (“
    -2.36
    ↵
    -2.27
    POSITIVE LOGITS
    鲼
    2.50
    硨
    2.47
     klarer
    2.30
     kredi
    2.25
     parut
    2.23
    bigr
    2.13
    瓛
    2.13
     groupe
    2.11
    ians
    2.09
     objectif
    2.09
    Activations Density 0.021%

    No Known Activations