© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116829
    Prev
    Next
    INDEX
    Explanations

    ASP.NET code and licenses

    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
    lett
    -0.74
    Outcome
    -0.70
    ائد
    -0.69
    杓
    -0.68
    iencias
    -0.65
    Result
    -0.65
    HeaderText
    -0.65
    ссмо
    -0.64
     deciduous
    -0.64
     unit
    -0.63
    POSITIVE LOGITS
     Waldo
    0.78
    смарт
    0.72
    icken
    0.72
     locust
    0.68
    ▬▬▬▬▬▬▬▬
    0.66
    羅斯
    0.66
     Anker
    0.65
     Бог
    0.64
    Lig
    0.63
     Obama
    0.63
    Activations Density 0.060%

    No Known Activations