© 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. 25747
    Prev
    Next
    INDEX
    Explanations

    code examples and implementation

    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
     воздей
    -0.96
    深入
    -0.95
     норма
    -0.94
     ermittelt
    -0.93
     predicate
    -0.93
     mankind
    -0.93
     measurable
    -0.90
    эш
    -0.90
    หา
    -0.89
    kių
    -0.89
    POSITIVE LOGITS
    ❼
    1.13
     estética
    1.05
    ⓪
    1.02
    aesthetic
    0.99
     olímp
    0.98
    ḿ
    0.98
    罒
    0.93
     aesthetic
    0.91
    snake
    0.91
     collaborators
    0.90
    Activations Density 0.355%

    No Known Activations