© 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. 109226
    Prev
    Next
    INDEX
    Explanations

    introduces field of study

    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
     avião
    -0.79
    小伙伴
    -0.78
     　　
    -0.78
     نقش
    -0.75
    ografía
    -0.75
     unwell
    -0.74
     stretching
    -0.73
    gment
    -0.73
     Granite
    -0.73
     đem
    -0.73
    POSITIVE LOGITS
     our
    0.96
    Euro
    0.88
     Encounter
    0.86
     boring
    0.85
     encountered
    0.82
     engineer
    0.81
    Encounter
    0.80
    ITest
    0.80
    ENGINE
    0.80
    deps
    0.79
    Activations Density 0.002%

    No Known Activations