© 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. 99792
    Prev
    Next
    INDEX
    Explanations

    `notice:`

    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
     was
    -1.68
    ↵↵↵
    -1.52
     At
    -1.42
     In
    -1.32
     it
    -1.30
     on
    -1.25
    ↵↵↵↵
    -1.23
    ,
    -1.23
    ↵↵↵↵↵
    -1.20
     Furthermore
    -1.20
    POSITIVE LOGITS
     jesteśmy
    1.77
    ogenicity
    1.58
    お値段
    1.57
    もう一度
    1.52
     that
    1.42
    ことがある
    1.37
    瀆
    1.37
     aussit
    1.36
    hanced
    1.35
     możliwe
    1.35
    Activations Density 0.012%

    No Known Activations