© 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. 84432
    Prev
    Next
    INDEX
    Explanations

    require or states

    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
    诸
    -0.92
    باره
    -0.90
     lesz
    -0.89
    美味しいです
    -0.86
     ว่า
    -0.85
    ås
    -0.83
     Martha
    -0.83
    它的
    -0.83
     W
    -0.82
    導入
    -0.82
    POSITIVE LOGITS
    кото
    1.00
    liani
    1.00
    excellents
    0.99
     démission
    0.97
    НИ
    0.97
     だっ
    0.96
    欒
    0.94
     but
    0.92
    ╥
    0.92
    РУ
    0.91
    Activations Density 0.012%

    No Known Activations