© 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. 50074
    Prev
    Next
    INDEX
    Explanations

    words starting with Thor

    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
    inephrine
    -0.78
    Asn
    -0.75
     Pratt
    -0.75
     USART
    -0.74
     Lav
    -0.74
    uteria
    -0.73
     Blat
    -0.73
    Npc
    -0.72
     invertebrates
    -0.72
     Suz
    -0.69
    POSITIVE LOGITS
    Thor
    1.01
     thor
    0.96
     Thor
    0.95
     THOR
    0.94
    ダース
    0.91
    thor
    0.90
     terça
    0.84
    THOR
    0.77
    rikan
    0.75
     equipes
    0.75
    Activations Density 0.029%

    No Known Activations