© 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. 67660
    Prev
    Next
    INDEX
    Explanations

    slash command or query parameter

    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
    once
    -0.92
    olf
    -0.87
    عتقد
    -0.84
    ini
    -0.83
    ole
    -0.81
    却
    -0.79
     przeprowad
    -0.77
    postDelayed
    -0.75
    ias
    -0.74
    uc
    -0.72
    POSITIVE LOGITS
     wherever
    0.86
     invitado
    0.85
     each
    0.83
    この日
    0.79
    ȷ
    0.76
     tomates
    0.76
     helicóptero
    0.75
    Vá
    0.75
     died
    0.74
     whatever
    0.74
    Activations Density 0.071%

    No Known Activations