© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77971
    Prev
    Next
    INDEX
    Explanations

    for those unfamiliar

    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
    usado
    -1.00
    tyk
    -0.95
    вів
    -0.94
    管理器
    -0.91
    !]
    -0.91
    Found
    -0.91
     とき
    -0.91
     argint
    -0.90
     diferite
    -0.90
    Auteur
    -0.89
    POSITIVE LOGITS
     unfamiliar
    2.19
     wondering
    1.54
     unaware
    1.46
    知らない
    1.21
     chưa
    1.16
     not
    1.16
     new
    1.15
     не
    1.10
     still
    1.09
     új
    1.08
    Activations Density 0.038%

    No Known Activations