© 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. 34-GEMMASCOPE-RES-131K
    4. 12043
    Prev
    Next
    INDEX
    Explanations

    URLs and textual content

    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_34/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
    ابط
    -0.85
    ——”
    -0.84
     ibn
    -0.81
     really
    -0.80
     garis
    -0.79
     ligiloj
    -0.76
    編集
    -0.75
    УП
    -0.75
     superfície
    -0.74
     tang
    -0.73
    POSITIVE LOGITS
     pity
    0.85
     disintegration
    0.84
    語言
    0.83
    Fiber
    0.81
    Asign
    0.78
    と思われます
    0.78
     Emits
    0.77
    摒
    0.76
     Fiber
    0.76
     Pity
    0.75
    Activations Density 0.001%

    No Known Activations