© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49381
    Prev
    Next
    INDEX
    Explanations

    word followed by all

    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
    MatInputModule
    -1.15
     derselben
    -1.05
    𝗴
    -1.02
     Каждый
    -0.99
     wahren
    -0.97
     fremden
    -0.97
     bestehende
    -0.96
     Verhältnisse
    -0.96
     Setiap
    -0.96
     каждого
    -0.95
    POSITIVE LOGITS
     all
    7.16
     все
    3.17
    all
    3.16
     tüm
    2.80
     ALL
    2.75
     всю
    2.73
     جميع
    2.67
    All
    2.67
     toute
    2.61
     semua
    2.42
    Activations Density 0.085%

    No Known Activations