© 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. 103268
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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
     distribución
    -0.88
     januar
    -0.87
    vetti
    -0.86
    няка
    -0.83
    前言
    -0.83
     convince
    -0.83
     mágica
    -0.83
     mentira
    -0.81
    moke
    -0.81
    ränken
    -0.79
    POSITIVE LOGITS
    MemoryWarning
    1.21
     memory
    0.94
     quedará
    0.76
     памяти
    0.75
     Araujo
    0.75
     jamás
    0.74
    Individ
    0.73
     forget
    0.73
     außer
    0.72
    льше
    0.72
    Activations Density 0.002%

    No Known Activations