© 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. 115634
    Prev
    Next
    INDEX
    Explanations

    providing or receiving support and help

    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
     grossesse
    -0.82
     HEIGHT
    -0.81
    kela
    -0.78
     cómics
    -0.77
     tesoro
    -0.77
     colombiano
    -0.77
    MMdd
    -0.76
     reproducibility
    -0.76
     와
    -0.75
    它们的
    -0.74
    POSITIVE LOGITS
     support
    1.99
     assistance
    1.98
     expert
    1.68
     help
    1.65
     guidance
    1.55
     adequate
    1.45
     appropriate
    1.43
     ongoing
    1.40
     proper
    1.34
     immediate
    1.34
    Activations Density 0.084%

    No Known Activations