© 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. 66599
    Prev
    Next
    INDEX
    Explanations

    Q: or /* followed by text

    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
     that
    -1.07
    していない
    -1.02
    ੧
    -0.99
     or
    -0.97
    有害
    -0.96
     to
    -0.95
     mikrofon
    -0.94
     socioeconomic
    -0.93
    érien
    -0.93
    tato
    -0.93
    POSITIVE LOGITS
     работает
    1.06
     culoare
    0.99
    celand
    0.99
     same
    0.98
     ib
    0.98
     bílé
    0.98
     pomaga
    0.94
    オリーブ
    0.94
     ameste
    0.93
     possibilità
    0.92
    Activations Density 0.000%

    No Known Activations