© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115814
    Prev
    Next
    INDEX
    Explanations

    produced and directed by

    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
     Effectiveness
    -0.81
     rechargeable
    -0.79
     Actors
    -0.77
     Spielen
    -0.75
    antwortung
    -0.72
    Effectiveness
    -0.72
    મ
    -0.71
     actress
    -0.69
     effectiveness
    -0.69
     Herbal
    -0.69
    POSITIVE LOGITS
     banner
    1.13
    directional
    0.94
    produced
    0.90
    banner
    0.87
    oznam
    0.84
     hulle
    0.84
    production
    0.83
     backing
    0.83
    ʲ
    0.81
    Banner
    0.81
    Activations Density 0.026%

    No Known Activations