© 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. 119071
    Prev
    Next
    INDEX
    Explanations

    demand

    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
     optimized
    -0.86
     optimization
    -0.85
     optimum
    -0.82
    WhereInput
    -0.81
     optimizing
    -0.80
     фир
    -0.79
     optimisation
    -0.77
    trade
    -0.75
     Opti
    -0.75
    po
    -0.75
    POSITIVE LOGITS
    demand
    0.84
     demanda
    0.83
     demand
    0.81
     demands
    0.80
    Solomon
    0.80
    capac
    0.78
    Capac
    0.77
    alibaba
    0.76
     Demand
    0.74
     Mei
    0.74
    Activations Density 0.021%

    No Known Activations