© 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. 71342
    Prev
    Next
    INDEX
    Explanations

    conditional logic and questions

    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
    いいのか
    -1.57
     alcune
    -1.55
    (!__
    -1.50
    鶿
    -1.47
     pesso
    -1.45
    魠
    -1.45
    
    -1.43
    蓠
    -1.42
    蹰
    -1.41
     verschillende
    -1.40
    POSITIVE LOGITS
     when
    2.09
     on
    2.02
     if
    1.84
     in
    1.76
     during
    1.66
     with
    1.60
     has
    1.55
     it
    1.52
     as
    1.52
     after
    1.49
    Activations Density 0.001%

    No Known Activations