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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85098
    Prev
    Next
    INDEX
    Explanations

    image

    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
    dáms
    -1.87
    縠
    -1.81
    ."
    -1.81
    龑
    -1.78
    天赋
    -1.68
     almeno
    -1.66
    畵
    -1.66
     scel
    -1.66
     uniquement
    -1.63
    aruhi
    -1.60
    POSITIVE LOGITS
     
    1.80
    ’
    1.63
    iſter
    1.62
     veren
    1.59
    os
    1.55
    8
    1.55
     “
    1.53
    进一步
    1.51
    ſſel
    1.51
    сила
    1.49
    Activations Density 0.014%

    No Known Activations