© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9348
    Prev
    Next
    INDEX
    Explanations

    obtain or discover details

    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
     or
    -1.73
     as
    -1.63
     to
    -1.53
     your
    -1.40
     How
    -1.34
    ức
    -1.30
     now
    -1.28
     our
    -1.25
     do
    -1.23
     since
    -1.23
    POSITIVE LOGITS
     didalam
    1.46
     londres
    1.38
     isolado
    1.32
    䊉
    1.30
     gouttes
    1.29
     sebag
    1.27
     WALT
    1.23
     UNIVERSIT
    1.23
     BUILDINGS
    1.23
     dieß
    1.22
    Activations Density 0.057%

    No Known Activations