© 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. 84212
    Prev
    Next
    INDEX
    Explanations

    XML comments and question/answer starters

    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
    樽
    -0.96
    六年
    -0.91
    九年
    -0.85
    flashdata
    -0.84
    ～！
    -0.82
    ymmetry
    -0.81
     UserRepository
    -0.81
     potem
    -0.80
    ARN
    -0.79
     leste
    -0.78
    POSITIVE LOGITS
     returns
    1.18
    returns
    0.99
     reu
    0.90
    Abbey
    0.84
     Bian
    0.83
     
    0.81
     plo
    0.80
     tunes
    0.77
    letics
    0.77
    Hostel
    0.77
    Activations Density 0.001%

    No Known Activations