© 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. 42003
    Prev
    Next
    INDEX
    Explanations

    black hole

    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
    chers
    -2.00
     aksesuar
    -1.84
    珧
    -1.73
    翃
    -1.70
     ambigu
    -1.68
     таких
    -1.66
     aga
    -1.63
    咈
    -1.62
    lossians
    -1.60
     dreadful
    -1.59
    POSITIVE LOGITS
     for
    1.97
     because
    1.77
     had
    1.75
     in
    1.74
     With
    1.73
     substantially
    1.73
     with
    1.70
     through
    1.67
     their
    1.60
    ？
    1.58
    Activations Density 0.012%

    No Known Activations