© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73845
    Prev
    Next
    INDEX
    Explanations

    Mr. titles

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

    The neuron strongly responds to occurrences of high‐level official titles and honorifics (e.g. “President,” “Vice President,” “Mr.,” “Chief Justice,” etc.).

    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
    个人
    -0.77
    ándo
    -0.76
    虽然
    -0.75
    申請
    -0.74
    排水
    -0.73
     kollek
    -0.72
    InRange
    -0.72
     SUPPORT
    -0.71
     erstat
    -0.71
     harte
    -0.71
    POSITIVE LOGITS
    omości
    0.84
    iace
    0.82
    Audience
    0.78
     PIX
    0.77
    ênd
    0.77
    ēju
    0.77
     beeind
    0.77
    rót
    0.76
     `/
    0.76
    ích
    0.76
    Activations Density 0.011%

    No Known Activations