© 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. 65513
    Prev
    Next
    INDEX
    Explanations

    vehicles and discovery

    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
     吗
    -0.78
    dificio
    -0.77
     anpass
    -0.74
    otsu
    -0.71
    :].
    -0.70
    Nonnull
    -0.70
     dataGridView
    -0.70
    teni
    -0.69
    ultural
    -0.69
    Sb
    -0.68
    POSITIVE LOGITS
     Defender
    1.27
    Defender
    1.07
    defender
    1.04
     Disco
    1.00
    Disco
    1.00
     disco
    0.92
     rover
    0.88
     Discovery
    0.88
     Rover
    0.88
     defender
    0.87
    Activations Density 0.002%

    No Known Activations