© 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. 7682
    Prev
    Next
    INDEX
    Explanations

    java, source, compliance, configuration flags

    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
    cB
    -0.78
     blob
    -0.77
     Immunity
    -0.74
     Tämä
    -0.73
    貽
    -0.73
    катерина
    -0.72
    domin
    -0.72
     flechas
    -0.72
    utzer
    -0.71
    ガーデン
    -0.71
    POSITIVE LOGITS
     source
    1.00
     compliance
    0.96
    source
    0.93
    源码
    0.84
    verbose
    0.84
     java
    0.82
     SOURCE
    0.80
     jav
    0.80
    Compliance
    0.79
     Jav
    0.78
    Activations Density 0.084%

    No Known Activations