© 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. 10-GEMMASCOPE-RES-131K
    7. 103170
    Prev
    Next
    INDEX
    Explanations

    draft

    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_10/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
    킁
    -3.03
    ῞
    -2.59
    ("'"
    -2.39
    
    -2.38
     ſever
    -2.36
    ᾐ
    -2.36
     dê
    -2.30
     wichtigsten
    -2.30
    鸕
    -2.27
    étaient
    -2.23
    POSITIVE LOGITS
    a
    4.22
    t
    2.61
    e
    2.59
    i
    2.58
    If
    2.56
    o
    2.47
     inga
    2.31
    I
    2.23
     семье
    2.23
    
    2.22
    Activations Density 0.010%

    No Known Activations