© 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. 65333
    Prev
    Next
    INDEX
    Explanations

    escaping special characters

    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
    ħħ
    -0.88
     enclosing
    -0.88
     replace
    -0.87
     replacing
    -0.86
    ということです
    -0.83
     enclose
    -0.79
    tuuri
    -0.78
     mottled
    -0.77
    olybden
    -0.77
     preceding
    -0.76
    POSITIVE LOGITS
    \.
    0.85
     gena
    0.84
    kä
    0.78
    offered
    0.77
    nect
    0.76
     _,
    0.76
     énorm
    0.74
     nami
    0.74
    exempt
    0.73
    > 
    0.73
    Activations Density 0.027%

    No Known Activations