© 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. 22-GEMMASCOPE-RES-131K
    7. 35778
    Prev
    Next
    INDEX
    Explanations

    new users or beginners

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

    The neuron detects language that signals newness or beginner/inexperienced users.

    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
     augusti
    -1.09
     Dunk
    -1.07
    游戏中
    -1.01
    ABAD
    -0.97
     sonora
    -0.94
    麻煩
    -0.92
     concor
    -0.91
     vitamina
    -0.90
    不夠
    -0.89
     بنات
    -0.87
    POSITIVE LOGITS
     inexperienced
    1.85
     beginners
    1.50
     beginner
    1.40
     rookie
    1.30
     rookies
    1.22
     novice
    1.20
     Beginners
    1.19
     Inex
    1.17
     newbies
    1.14
     learning
    1.13
    Activations Density 0.084%

    No Known Activations