© 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. 22-GEMMASCOPE-RES-131K
    7. 84045
    Prev
    Next
    INDEX
    Explanations

    multiple choice option letters

    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
    lumi
    -1.07
    嘅
    -1.02
     voegen
    -1.00
     what
    -0.99
    ᚑ
    -0.98
    zta
    -0.97
     mitä
    -0.97
    ܜ
    -0.96
    znej
    -0.96
    响起
    -0.96
    POSITIVE LOGITS
     immedi
    1.12
     cambiamento
    1.05
     vieler
    0.97
     cambios
    0.97
    both
    0.94
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.93
     wielu
    0.93
    ↵↵↵↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.92
    Activations Density 0.003%

    No Known Activations