© 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. 89952
    Prev
    Next
    INDEX
    Explanations

    hot-button 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
    стам
    -0.89
    жере
    -0.87
    บัติ
    -0.84
     natin
    -0.83
    xically
    -0.81
    eleste
    -0.81
    pact
    -0.80
    矣
    -0.80
    hander
    -0.79
    ASIS
    -0.77
    POSITIVE LOGITS
     issues
    7.03
     issue
    6.34
    issues
    5.25
     Issues
    5.00
    Issues
    4.84
    issue
    4.81
    Issue
    4.44
     Issue
    4.31
     ISSUES
    4.22
    ISSUES
    3.77
    Activations Density 0.138%

    No Known Activations