© 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. 102621
    Prev
    Next
    INDEX
    Explanations

    post-nominal titles and honorifics

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

    The neuron detects post-nominal honorific abbreviations (e.g. OBE, CMG, FRS, CBE, PC) following personal names.

    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
     quaisquer
    -1.42
     Scritto
    -1.34
     Tells
    -1.32
     любых
    -1.31
    ógico
    -1.30
     kuhusu
    -1.30
     любые
    -1.27
     装修
    -1.26
     its
    -1.26
     any
    -1.26
    POSITIVE LOGITS
    ↵↵
    1.38
    9
    1.37
    izacja
    1.30
     müsse
    1.18
     hätte
    1.16
    grond
    1.16
    tellung
    1.14
     Kühlschrank
    1.13
    crackers
    1.12
    peka
    1.11
    Activations Density 0.029%

    No Known Activations