© 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. 10-GEMMASCOPE-RES-131K
    7. 123938
    Prev
    Next
    INDEX
    Explanations

    annotations

    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_10/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
    what
    -2.45
    )
    -2.42
    ться
    -2.42
    ten
    -2.19
    te
    -2.17
    to
    -2.11
    后
    -2.09
     跟
    -1.95
    榈
    -1.91
     funktionieren
    -1.90
    POSITIVE LOGITS
    skjaer
    2.72
    跸
    2.64
    annotations
    2.63
    谖
    2.61
    ஂ
    2.52
    逺
    2.47
    
    2.45
     så
    2.45
    ჱ
    2.39
    勦
    2.33
    Activations Density 0.002%

    No Known Activations