© 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. 34-GEMMASCOPE-RES-131K
    7. 50172
    Prev
    Next
    INDEX
    Explanations

    living room features

    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_34/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
     kellett
    -1.20
     zodat
    -1.04
     weten
    -1.02
     BioLib
    -0.98
    sieht
    -0.98
     vertellen
    -0.96
     that
    -0.93
    arschijnlijk
    -0.90
     for
    -0.90
    用于
    -0.90
    POSITIVE LOGITS
     features
    3.30
     feature
    2.83
     featuring
    2.70
    Featuring
    2.56
     featured
    2.42
     Featuring
    2.38
    features
    2.28
    Features
    2.14
     Features
    2.06
     offers
    2.05
    Activations Density 0.074%

    No Known Activations