© 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. 66104
    Prev
    Next
    INDEX
    Explanations

    Objective-C class declarations

    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
    ⎫
    -0.82
     containing
    -0.81
     Tuchel
    -0.75
     yards
    -0.75
    OTS
    -0.75
     Cristiano
    -0.74
     Statute
    -0.74
    žení
    -0.74
     search
    -0.74
     acids
    -0.74
    POSITIVE LOGITS
     vě
    0.74
    шные
    0.73
     применять
    0.72
     Moreira
    0.72
    ganan
    0.71
    ᱛ
    0.68
     внимания
    0.65
    ыр
    0.65
     kö
    0.65
     kejadian
    0.65
    Activations Density 0.041%

    No Known Activations