© 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. 109612
    Prev
    Next
    INDEX
    Explanations

    domains and issues

    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
    municipi
    -0.88
    沦
    -0.85
     caracter
    -0.83
    dataflow
    -0.83
     اشاره
    -0.81
     aprove
    -0.81
    Приятного
    -0.79
    ͉
    -0.79
    nhà
    -0.76
    あぁ
    -0.76
    POSITIVE LOGITS
     scenario
    1.02
     Scenario
    0.98
    醯
    0.88
     Fraternity
    0.83
     HRC
    0.82
     escrit
    0.82
    Equations
    0.81
     precede
    0.81
    フォーマ
    0.80
    Scenario
    0.79
    Activations Density 0.048%

    No Known Activations