© 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. 90714
    Prev
    Next
    INDEX
    Explanations

    jackson, annotation, Message

    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
     havent
    -0.87
     expect
    -0.86
    踵
    -0.82
    虜
    -0.82
     Additions
    -0.82
     eld
    -0.81
    𝗍
    -0.79
     增加
    -0.78
     epistle
    -0.78
     chateau
    -0.78
    POSITIVE LOGITS
     envers
    0.92
     boyunca
    0.86
    éhez
    0.82
    に似
    0.81
    SpringRunner
    0.79
     fanáticos
    0.79
    昔から
    0.79
    according
    0.78
     étrangères
    0.78
    ことも
    0.77
    Activations Density 0.005%

    No Known Activations