© 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. 34568
    Prev
    Next
    INDEX
    Explanations

    http urls

    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
    шого
    -0.81
     equinox
    -0.79
    smi
    -0.75
    rud
    -0.74
     beeswax
    -0.73
    rando
    -0.73
     Rising
    -0.73
     chạy
    -0.72
     Harris
    -0.71
    xxxx
    -0.71
    POSITIVE LOGITS
    Răsp
    0.88
    Sådan
    0.87
     lingered
    0.86
    Özel
    0.80
    Elenco
    0.80
    Algemeen
    0.80
    Investi
    0.78
    Salu
    0.77
     Implements
    0.77
    Weiterlesen
    0.77
    Activations Density 0.007%

    No Known Activations