© 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. 22-GEMMASCOPE-RES-131K
    4. 28514
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and structure

    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_22/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
     endearing
    -1.06
     decadent
    -1.02
     ingrained
    -1.02
    fjspx
    -1.02
     two
    -1.02
    It
    -1.02
    页面存档备份
    -1.01
    "
    -1.00
    ós
    -1.00
     determining
    -0.98
    POSITIVE LOGITS
     pouvons
    1.19
    色は
    1.13
    testable
    1.13
    wakili
    1.11
    ecause
    1.07
     possibilités
    1.05
     which
    1.04
    hese
    1.04
    nourriture
    1.03
    ungkapkan
    1.02
    Activations Density 0.007%

    No Known Activations