© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79093
    Prev
    Next
    INDEX
    Explanations

    Copyright comments preceding summary

    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
     東京都
    -0.82
     Fertilizer
    -0.75
    Tester
    -0.69
     bahkan
    -0.67
     padd
    -0.66
     בס
    -0.65
    死去
    -0.64
     entgeg
    -0.63
    Testing
    -0.63
    System
    -0.63
    POSITIVE LOGITS
     summaries
    1.00
     Summa
    0.99
     aucun
    0.95
    ṁ
    0.95
     nogal
    0.85
     heen
    0.84
    PARAMS
    0.80
     Amit
    0.80
     agricoles
    0.80
     ejecución
    0.79
    Activations Density 0.023%

    No Known Activations