© 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. 130599
    Prev
    Next
    INDEX
    Explanations

    code parentheses

    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
    ኧ
    -3.27
    
    -3.16
    ]
    -2.67
     This
    -2.64
    戗
    -2.63
    戋
    -2.59
     is
    -2.48
     Segurança
    -2.47
    薆
    -2.45
    ൎ
    -2.38
    POSITIVE LOGITS
    ())
    2.56
    啱
    2.52
    她
    2.50
     they
    2.48
    n
    2.42
    觥
    2.39
    ↵↵
    2.33
    店铺
    2.19
    z
    2.19
     beendet
    2.17
    Activations Density 0.001%

    No Known Activations