© 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. 106734
    Prev
    Next
    INDEX
    Explanations

    font size units

    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
    ֊
    -0.86
    ::<
    -0.82
    ارع
    -0.78
    scraper
    -0.76
     Revolución
    -0.76
     =>
    -0.76
     certaine
    -0.76
    ̏
    -0.74
     Förderung
    -0.74
     erforder
    -0.74
    POSITIVE LOGITS
    px
    1.18
     size
    1.01
     размере
    0.95
    size
    0.93
     два
    0.88
    ″
    0.88
     weight
    0.87
     Jonah
    0.87
     wirken
    0.85
     tamaño
    0.85
    Activations Density 0.004%

    No Known Activations