© 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. 71090
    Prev
    Next
    INDEX
    Explanations

    founded after

    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
     you
    -1.73
    0
    -1.60
     вони
    -1.56
     prace
    -1.44
     they
    -1.41
     ones
    -1.41
     hacían
    -1.38
    俢
    -1.37
    ↵
    -1.35
    ATION
    -1.34
    POSITIVE LOGITS
     to
    1.42
     각
    1.38
    それぞれの
    1.36
     logró
    1.34
     sate
    1.32
    inafter
    1.31
     recog
    1.27
     "`
    1.25
    鉚
    1.24
    бран
    1.23
    Activations Density 0.287%

    No Known Activations