© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99944
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts and code

    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
    dication
    -0.85
     druk
    -0.84
    𝑪
    -0.84
     Gesetz
    -0.84
    今週
    -0.83
     促销
    -0.82
     مرجع
    -0.81
     deportivos
    -0.78
    šana
    -0.77
    我が
    -0.77
    POSITIVE LOGITS
     JMenuItem
    0.89
     ?>>
    0.86
    setHas
    0.86
     SearchView
    0.85
     getItemCount
    0.83
    āti
    0.81
     getPassword
    0.81
    ionario
    0.81
    toxicity
    0.79
    HashTable
    0.79
    Activations Density 0.102%

    No Known Activations