© 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. 22-GEMMASCOPE-RES-131K
    7. 39770
    Prev
    Next
    INDEX
    Explanations

    web links to code

    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
     for
    -1.53
     first
    -1.20
    ↵↵
    -1.14
    mathrm
    -1.09
     both
    -1.06
     should
    -1.05
    nees
    -1.03
     as
    -1.02
    TheReal
    -1.01
    OfThe
    -0.99
    POSITIVE LOGITS
     maniere
    1.58
    えっ
    1.34
     applau
    1.30
     sirop
    1.28
    삵
    1.27
    
    1.26
     trám
    1.25
     perpé
    1.22
    殽
    1.22
    쫀
    1.20
    Activations Density 0.001%

    No Known Activations