© 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. 81284
    Prev
    Next
    INDEX
    Explanations

    concepts like or of

    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
     parejas
    -1.17
    那些
    -1.09
     celle
    -1.09
    每个
    -1.08
     ceux
    -1.04
    şit
    -1.00
     dérou
    -0.99
     bandoulière
    -0.99
    ều
    -0.98
    ļi
    -0.97
    POSITIVE LOGITS
     like
    5.28
     such
    4.56
     такого
    3.22
     ilyen
    2.75
     this
    2.73
     подоб
    2.72
     of
    2.69
     như
    2.56
     seperti
    2.55
    このような
    2.42
    Activations Density 0.072%

    No Known Activations