© 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. 13697
    Prev
    Next
    INDEX
    Explanations

    XML declarations and code snippets

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

    The neuron detects chapter‐and‐verse reference tokens (the numeric “chapter:verse” patterns and related punctuation in biblical citations).

    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
     ——
    -1.12
     lucru
    -1.06
     desaparición
    -1.05
     ihres
    -1.03
     ceea
    -1.02
     unul
    -1.00
     tuturor
    -0.99
     ihrer
    -0.99
    徜
    -0.98
    ว์
    -0.97
    POSITIVE LOGITS
     says
    1.19
    しましたが
    1.04
     where
    1.04
     dokonce
    1.04
     japones
    1.02
     embuti
    1.02
     bordado
    1.01
     camuf
    1.01
     estampado
    1.00
     volantes
    1.00
    Activations Density 0.006%

    No Known Activations