© 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. 22-GEMMASCOPE-RES-131K
    7. 35038
    Prev
    Next
    INDEX
    Explanations

    compatibility code or libraries

    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
    鷂
    -2.23
     in
    -2.22
    嫫
    -2.20
    恫
    -2.13
    硖
    -2.08
     mengakibatkan
    -2.05
     now
    -2.03
    maları
    -2.02
    
    -2.02
     time
    -2.00
    POSITIVE LOGITS
    6
    3.66
    5
    3.63
    7
    3.61
    8
    3.50
    ’
    3.42
    4
    3.27
    9
    3.13
    2
    2.98
    0
    2.86
    which
    2.69
    Activations Density 0.001%

    No Known Activations