© 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. 92270
    Prev
    Next
    INDEX
    Explanations

    SQL CREATE TABLE statements

    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
    IActionResult
    -0.90
    малар
    -0.88
    abril
    -0.73
    CLIENT
    -0.72
     suspicion
    -0.72
     Krü
    -0.71
    alties
    -0.68
     squir
    -0.68
    чек
    -0.68
     αποτε
    -0.68
    POSITIVE LOGITS
     podpor
    0.85
     structs
    0.78
     cast
    0.77
    keth
    0.77
     ARRAY
    0.76
    Oakland
    0.75
    Requiem
    0.75
     모든
    0.75
     map
    0.74
     CAST
    0.74
    Activations Density 0.038%

    No Known Activations