© 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. 66019
    Prev
    Next
    INDEX
    Explanations

    platform specific

    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
     laymen
    -0.88
     and
    -0.79
     powiet
    -0.78
    がり
    -0.75
     hyg
    -0.74
    흑
    -0.72
     ragged
    -0.71
     States
    -0.71
    くれる
    -0.71
    愫
    -0.70
    POSITIVE LOGITS
     Plat
    0.99
    Plat
    0.92
     CGPoint
    0.90
     farbe
    0.88
     Enix
    0.87
    veyard
    0.87
    ciera
    0.86
    ühungen
    0.85
    specific
    0.85
    SPECIFIC
    0.83
    Activations Density 0.016%

    No Known Activations