© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106468
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and quality descriptions

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

    The neuron specializes in picking out formal salutations and courteous phrasing—polite address terms and expressions of deference or thanks.

    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
    lüssel
    -0.84
    哇
    -0.83
    BOLD
    -0.81
    Ultimate
    -0.81
    CELONA
    -0.80
    krut
    -0.80
    middelen
    -0.80
     tampoco
    -0.79
    хіво
    -0.79
    如图
    -0.79
    POSITIVE LOGITS
    esteem
    1.10
     esteem
    0.86
     tokens
    0.85
     manifesta
    0.82
     grateful
    0.82
     дру
    0.81
    すぎ
    0.80
     хиру
    0.80
    ginate
    0.79
     espont
    0.79
    Activations Density 0.020%

    No Known Activations