© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73743
    Prev
    Next
    INDEX
    Explanations

    Luigi followed by names, avant garde

    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_10/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
    “
    -4.47
    ’
    -4.09
    2
    -3.94
    1
    -3.88
     “
    -3.44
    *
    -3.09
    I
    -2.92
    .,
    -2.92
    3
    -2.89
    T
    -2.88
    POSITIVE LOGITS
     ſou
    3.36
    
    3.00
    
    2.94
    ୌ
    2.92
     jugado
    2.92
    媖
    2.89
    蜮
    2.88
    嚶
    2.80
    
    2.77
     pagado
    2.72
    Activations Density 0.005%

    No Known Activations