© 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. 98681
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
     way
    -0.82
     deniz
    -0.82
    قا
    -0.81
     wey
    -0.73
    たとえば
    -0.72
     conjunction
    -0.71
    setNum
    -0.70
     someplace
    -0.70
     afore
    -0.69
    OTO
    -0.69
    POSITIVE LOGITS
     relating
    3.59
     relate
    3.44
     relates
    3.19
     relation
    2.69
    rel
    2.56
     related
    2.53
    relate
    2.48
     Relating
    2.33
     relat
    2.28
    Rel
    2.16
    Activations Density 0.132%

    No Known Activations