© 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. 57531
    Prev
    Next
    INDEX
    Explanations

    property listings

    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
     what
    -1.55
     different
    -1.46
     может
    -1.42
     помогает
    -1.36
     various
    -1.34
    渽
    -1.30
     verschiedenen
    -1.29
    色んな
    -1.28
     same
    -1.27
     даже
    -1.23
    POSITIVE LOGITS
    llllll
    1.51
     object
    1.37
     Tabelle
    1.33
    woord
    1.32
    llll
    1.31
     fieles
    1.30
    Phaser
    1.30
    lllllllll
    1.30
    usions
    1.29
    лах
    1.29
    Activations Density 0.055%

    No Known Activations