© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41538
    Prev
    Next
    INDEX
    Explanations

    Massachusetts cities and regions

    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_10/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
    慙
    -1.61
     drei
    -1.55
    Krankheitsbild
    -1.53
     小学校
    -1.52
     captivating
    -1.52
    が少ない
    -1.52
     unn
    -1.51
     porque
    -1.51
     peuvent
    -1.50
     ferocious
    -1.48
    POSITIVE LOGITS
    </td>
    2.13
     or
    1.63
     not
    1.63
     innumerable
    1.61
     both
    1.56
     burgeoning
    1.55
     countless
    1.53
     boasts
    1.48
     phenomenal
    1.48
    مام
    1.47
    Activations Density 0.018%

    No Known Activations