© 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. 118363
    Prev
    Next
    INDEX
    Explanations

    network router and features

    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
     breaking
    -1.02
     Breaking
    -0.92
     broke
    -0.91
     breakup
    -0.90
    breaking
    -0.87
     Break
    -0.86
    Breaking
    -0.85
     break
    -0.85
    break
    -0.85
     breakage
    -0.84
    POSITIVE LOGITS
     ASF
    0.81
     ADVANCED
    0.80
     parental
    0.77
    krut
    0.77
     LEDs
    0.77
    čių
    0.76
     manu
    0.75
     genie
    0.73
    が変わ
    0.72
    ジン
    0.71
    Activations Density 0.021%

    No Known Activations