© 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. 48307
    Prev
    Next
    INDEX
    Explanations

    accepts_nested_attributes_for

    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
    膣
    -0.82
    ẾT
    -0.78
     adrenal
    -0.76
    딕
    -0.75
    真っ
    -0.74
    ᄂ
    -0.74
    atud
    -0.73
     cabinets
    -0.72
     chemicals
    -0.72
    Mockito
    -0.71
    POSITIVE LOGITS
     veder
    0.76
     DMR
    0.76
    انى
    0.73
    moments
    0.72
    それぞれの
    0.72
    さみ
    0.72
    Toler
    0.71
     sindaco
    0.69
    ampl
    0.69
    جات
    0.68
    Activations Density 0.022%

    No Known Activations