© 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. 110834
    Prev
    Next
    INDEX
    Explanations

    aircraft and autogyros

    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
    તા
    -0.91
     shepherds
    -0.79
    xmm
    -0.76
    ләр
    -0.75
    secutions
    -0.75
     mieście
    -0.75
    Iterator
    -0.73
    ಸ
    -0.73
    City
    -0.72
    CITY
    -0.70
    POSITIVE LOGITS
     sanitaire
    0.84
    wooden
    0.83
     pikiran
    0.79
     bip
    0.76
     Solo
    0.76
    trainer
    0.76
    Solo
    0.75
    perusahaan
    0.74
     wooden
    0.74
    transaksi
    0.73
    Activations Density 0.030%

    No Known Activations