© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43510
    Prev
    Next
    INDEX
    Explanations

    numerical scores out of 10

    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
    
    -2.16
    噥
    -2.02
    ጢ
    -1.98
    嫫
    -1.94
    ༔
    -1.90
    鹚
    -1.90
    🪆
    -1.88
    婼
    -1.87
    ”;
    -1.87
    -<
    -1.84
    POSITIVE LOGITS
     of
    2.77
    8
    2.23
    0
    2.20
    1
    2.09
    3
    2.05
    5
    1.91
    2
    1.90
    .
    1.85
    when
    1.80
    9
    1.80
    Activations Density 0.008%

    No Known Activations