© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64406
    Prev
    Next
    INDEX
    Explanations

    has been

    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
    Ẓ
    -1.59
    AZIONI
    -1.38
    produzione
    -1.37
    Ḳ
    -1.35
     lenne
    -1.34
     gehabt
    -1.32
     lesz
    -1.23
    をしていた
    -1.23
    
    -1.23
    囘
    -1.17
    POSITIVE LOGITS
     has
    8.31
     have
    6.59
     telah
    4.75
     đã
    4.31
     έχει
    3.66
     olmuş
    3.09
     نے
    2.97
     έχουν
    2.84
     heeft
    2.83
    已经
    2.73
    Activations Density 1.543%

    No Known Activations