© 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. 47893
    Prev
    Next
    INDEX
    Explanations

    python class definitions

    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
     judges
    -0.72
    letto
    -0.71
     Maple
    -0.71
    قف
    -0.71
    idenav
    -0.69
    reserv
    -0.68
     on
    -0.67
     Aluno
    -0.66
    جهة
    -0.66
    Oph
    -0.66
    POSITIVE LOGITS
     client
    0.93
    client
    0.82
     SCIENCES
    0.81
     clients
    0.80
     response
    0.78
    assertEquals
    0.78
    Client
    0.76
    mox
    0.76
     test
    0.75
     setUp
    0.75
    Activations Density 0.003%

    No Known Activations