© 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. 10-GEMMASCOPE-RES-131K
    7. 71135
    Prev
    Next
    INDEX
    Explanations

    syllables ending in u

    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
    {
    -2.77
    Also
    -2.77
    an
    -2.64
    ;
    -2.58
     neue
    -2.28
    ].
    -2.28
    ',
    -2.28
    蚡
    -2.25
     Then
    -2.25
    tafogo
    -2.19
    POSITIVE LOGITS
    
    3.13
    ’;
    3.02
    梣
    2.92
    穑
    2.91
     exé
    2.86
    鈊
    2.83
    餿
    2.80
    荜
    2.77
     crée
    2.69
    ⎘
    2.69
    Activations Density 0.235%

    No Known Activations