© 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. 60865
    Prev
    Next
    INDEX
    Explanations

    .NET server client code

    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
     став
    -0.72
    禄
    -0.70
     Pity
    -0.67
    Governance
    -0.67
     HEADER
    -0.66
     العن
    -0.66
    micas
    -0.66
    所以我
    -0.66
     sister
    -0.65
    DataContext
    -0.65
    POSITIVE LOGITS
    ctl
    0.84
     post
    0.84
    VIEW
    0.83
    enschappelijke
    0.83
    бат
    0.82
     doPost
    0.81
     VIEW
    0.79
    getPost
    0.79
    brochen
    0.77
     hovor
    0.77
    Activations Density 0.118%

    No Known Activations