© 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. 34-GEMMASCOPE-RES-131K
    7. 103158
    Prev
    Next
    INDEX
    Explanations

    the word "include"

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    {~
    -1.02
     meander
    -0.99
    </h1>
    -0.98
     edifice
    -0.97
     intérieure
    -0.97
    </i>
    -0.96
    冠军
    -0.93
    E
    -0.93
    生まれ
    -0.91
    包括
    -0.90
    POSITIVE LOGITS
     all
    1.15
    guiente
    1.02
    ريات
    0.97
    龥
    0.96
     Every
    0.94
    ﻒ
    0.93
     tenden
    0.93
    forall
    0.93
    ナメント
    0.92
     Everyone
    0.91
    Activations Density 0.032%

    No Known Activations