© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    not precedential

    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
    方が
    -0.71
    ﻮ
    -0.69
    굴
    -0.68
    Guardians
    -0.67
     இரு
    -0.67
     Carrier
    -0.67
    ルム
    -0.67
     पनि
    -0.66
     карьер
    -0.66
    oinette
    -0.66
    POSITIVE LOGITS
    jet
    0.88
    vstack
    0.83
     Jika
    0.82
     wire
    0.82
     TALL
    0.81
    
    0.80
    OVA
    0.79
    wire
    0.77
     TAIL
    0.76
     ایده
    0.76
    Activations Density 0.003%

    No Known Activations