© 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. 82708
    Prev
    Next
    INDEX
    Explanations

    Licensed software notices

    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
     категории
    -0.74
     губ
    -0.68
     ถ
    -0.68
     müsse
    -0.68
    になったら
    -0.67
    只想
    -0.66
     encro
    -0.66
    ornment
    -0.66
    上下
    -0.65
     ["
    -0.65
    POSITIVE LOGITS
     highs
    0.81
    akos
    0.81
    AAT
    0.80
    回目の
    0.80
    ']))
    0.79
     Geller
    0.79
     strengthens
    0.78
    Chili
    0.78
     jedi
    0.78
     maintenance
    0.77
    Activations Density 0.003%

    No Known Activations