© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93825
    Prev
    Next
    INDEX
    Explanations

    assuming X is positive

    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
    länder
    -0.95
     surla
    -0.93
     Alors
    -0.88
    自制
    -0.84
    zemu
    -0.83
     länder
    -0.83
     Vorg
    -0.82
     bagus
    -0.81
     fidé
    -0.81
     København
    -0.79
    POSITIVE LOGITS
    -------
    
    0.94
     already
    0.88
     again
    0.83
    openapi
    0.81
     bemerkt
    0.79
    중
    0.78
    핑
    0.75
     Skilled
    0.75
    fox
    0.74
    ')['
    0.74
    Activations Density 0.069%

    No Known Activations