© 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. 22-GEMMASCOPE-RES-131K
    4. 93126
    Prev
    Next
    INDEX
    Explanations

    past tense verbs in religious texts

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

    The neuron fires on words that express supplication, trust, or deliverance in a religious context—i.e. verbs and nouns involved in crying out to or trusting in God.

    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
    為に
    -1.83
     However
    -1.35
     when
    -1.32
    感じです
    -1.28
     their
    -1.25
    habitude
    -1.24
    感じが
    -1.24
     wichtiger
    -1.23
     careful
    -1.23
     provide
    -1.22
    POSITIVE LOGITS
    を
    1.60
    も
    1.58
    は
    1.54
    に
    1.52
    が
    1.50
     oeil
    1.48
     secondes
    1.35
    atürk
    1.34
     hiver
    1.34
    や
    1.32
    Activations Density 0.016%

    No Known Activations