© 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. 90388
    Prev
    Next
    INDEX
    Explanations

    Infamous, Model, rehabilitation

    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
    paste
    -0.75
    chien
    -0.73
    ecause
    -0.72
    alai
    -0.71
    FLO
    -0.71
    гами
    -0.70
     determinada
    -0.70
     shock
    -0.70
    empor
    -0.70
    UCT
    -0.68
    POSITIVE LOGITS
    后者
    0.89
    的技术
    0.87
     latter
    0.87
     bgcolor
    0.84
     печени
    0.80
     Wilmington
    0.77
    的过程中
    0.75
    貸切
    0.73
    ου
    0.73
    兩種
    0.73
    Activations Density 0.001%

    No Known Activations