© 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. 2248
    Prev
    Next
    INDEX
    Explanations

    testing terms like feasibility, viability, durability

    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
     dicas
    -1.09
    examined
    -1.02
    analy
    -0.87
     pozn
    -0.86
    studied
    -0.85
     atención
    -0.83
    cleaned
    -0.83
     иссле
    -0.83
    露出了
    -0.81
     datos
    -0.81
    POSITIVE LOGITS
     feasibility
    1.30
     comprehensive
    1.25
     compatibility
    1.20
     preliminary
    1.17
     toxicity
    1.16
     viability
    1.15
     thorough
    1.12
     usability
    1.09
    toxicity
    1.05
     durability
    1.05
    Activations Density 0.156%

    No Known Activations