© 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. 70159
    Prev
    Next
    INDEX
    Explanations

    Mrnjavac, Sultanova-Zhdanova, Krnaich, Bteghrine, Mnejja1

    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
    誼
    -0.85
    arder
    -0.82
     virtually
    -0.81
     many
    -0.81
    folg
    -0.78
    任務
    -0.75
     Invoice
    -0.74
     just
    -0.74
    atase
    -0.74
    誕
    -0.73
    POSITIVE LOGITS
     Huguen
    0.84
     connecter
    0.82
    EVER
    0.81
     coti
    0.81
    AILY
    0.81
    ității
    0.81
     인터
    0.78
     procra
    0.77
    tists
    0.76
     preoc
    0.76
    Activations Density 0.039%

    No Known Activations