© 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. 91115
    Prev
    Next
    INDEX
    Explanations

    A: barry / a:

    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
    ประก
    -0.84
     картофе
    -0.81
    ้อมูล
    -0.80
    arbeit
    -0.79
     çar
    -0.78
     sabah
    -0.77
     Zong
    -0.76
    入れた
    -0.75
     conclure
    -0.74
    に残
    -0.73
    POSITIVE LOGITS
     tutor
    0.83
     Numerade
    0.81
     mRNA
    0.78
     Helden
    0.77
     Profesor
    0.77
    permum
    0.77
    らく
    0.75
    diği
    0.75
     PGA
    0.73
    ровки
    0.72
    Activations Density 0.037%

    No Known Activations