© 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. 70823
    Prev
    Next
    INDEX
    Explanations

    quotes around nouns

    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
    绝望
    -0.99
    鶿
    -0.97
    Cinta
    -0.96
     Profesor
    -0.95
     yaka
    -0.94
    鲜血
    -0.93
     kopi
    -0.92
    archical
    -0.91
    面试
    -0.91
    ernoo
    -0.90
    POSITIVE LOGITS
    ࣭
    0.99
    continue
    0.98
    està
    0.96
     bílé
    0.93
    ığını
    0.93
    ∽
    0.92
     allerede
    0.92
    𓂂
    0.92
     оборудования
    0.91
    硅
    0.90
    Activations Density 0.028%

    No Known Activations