© 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. 59769
    Prev
    Next
    INDEX
    Explanations

    code comments and imports

    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
     Also
    -1.57
     trataba
    -1.53
     sedangkan
    -1.52
    珦
    -1.52
     to
    -1.51
    嵛
    -1.48
    Also
    -1.44
     reunió
    -1.41
     lhes
    -1.38
     brilliantly
    -1.38
    POSITIVE LOGITS
     and
    2.16
    quartered
    1.45
     mln
    1.42
     fhould
    1.40
     fhall
    1.38
     lal
    1.36
     castig
    1.33
    婊
    1.33
     fupp
    1.31
    ⢊
    1.30
    Activations Density 0.007%

    No Known Activations