© 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. 2461
    Prev
    Next
    INDEX
    Explanations

    describing previously performed methods

    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
    不好
    -1.02
    czne
    -0.92
     proposés
    -0.91
     verschiedene
    -0.91
     انواع
    -0.90
    toObject
    -0.90
    ść
    -0.88
    ilyen
    -0.87
    oleum
    -0.85
    IBar
    -0.85
    POSITIVE LOGITS
     described
    2.05
     previously
    1.70
     according
    1.66
     описа
    1.55
    described
    1.47
     Described
    1.34
     essentially
    1.30
     descrit
    1.27
     beschrieben
    1.27
     décrit
    1.23
    Activations Density 0.117%

    No Known Activations