© 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. 39882
    Prev
    Next
    INDEX
    Explanations

    Hollywood Blvd

    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
    polski
    -1.00
     Finally
    -1.00
    ㄱ
    -0.99
    武将
    -0.98
    président
    -0.97
     vœux
    -0.95
    偲
    -0.95
    ılı
    -0.94
    но
    -0.94
    СР
    -0.93
    POSITIVE LOGITS
     if
    1.25
    if
    1.13
     firstly
    1.02
     who
    1.00
    焄
    0.95
     accordance
    0.93
    centred
    0.90
     switch
    0.89
     return
    0.89
     (!__
    0.89
    Activations Density 0.009%

    No Known Activations