© 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. 34-GEMMASCOPE-RES-131K
    4. 118099
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun "his"

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

    This neuron specializes in spotting Biblical or religious verses (e.g., Psalm‐style passages with verse numbers, archaic phrasing like “sing unto the Lord,” “bless,” “heathen,” 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
    Она
    -1.70
    她也
    -1.68
     вона
    -1.62
    她們
    -1.62
    They
    -1.56
    彼女は
    -1.53
     она
    -1.49
     которое
    -1.46
    She
    -1.44
     mereka
    -1.42
    POSITIVE LOGITS
     his
    11.38
     его
    6.66
     jego
    6.41
     hänen
    5.00
    他的
    4.91
     njego
    4.69
     його
    4.66
    彼の
    4.66
     His
    4.53
    his
    4.53
    Activations Density 0.274%

    No Known Activations