© 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. 130409
    Prev
    Next
    INDEX
    Explanations

    XML namespaces

    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
     but
    -2.31
     Both
    -2.14
     However
    -1.96
    
    -1.80
    te
    -1.79
    𖣘
    -1.72
    numel
    -1.70
     Neither
    -1.69
     It
    -1.68
     erwähnt
    -1.66
    POSITIVE LOGITS
     that
    2.47
    英寸
    1.95
    M
    1.88
    S
    1.87
    V
    1.80
    álise
    1.79
     arv
    1.78
     deres
    1.77
     insum
    1.76
     kasa
    1.74
    Activations Density 0.005%

    No Known Activations