© 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. 85049
    Prev
    Next
    INDEX
    Explanations

    processes underlying

    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
    ՚
    -1.70
    ࿆
    -1.56
    only
    -1.55
    să
    -1.52
    !?"
    -1.46
     lixo
    -1.45
    驁
    -1.45
    合适
    -1.42
     behulp
    -1.41
    !!"
    -1.38
    POSITIVE LOGITS
     —
    1.45
    és
    1.40
    {
    1.35
     :
    1.33
     статті
    1.28
     in
    1.27
    脯
    1.27
     При
    1.23
     -
    1.23
    Furthermore
    1.23
    Activations Density 0.061%

    No Known Activations