© 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. 22-GEMMASCOPE-RES-131K
    7. 36275
    Prev
    Next
    INDEX
    Explanations

    numbers and measures

    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_22/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
     rö
    -0.92
     puntuación
    -0.91
     valoración
    -0.90
    resultat
    -0.90
    unica
    -0.86
    förder
    -0.85
     energético
    -0.84
     آنان
    -0.84
     garantir
    -0.84
     grö
    -0.84
    POSITIVE LOGITS
     additional
    1.12
     increase
    1.11
    ystemet
    1.09
     increased
    1.05
     added
    1.02
    เพิ่ม
    1.02
    ڻ
    0.93
     adding
    0.92
     add
    0.91
    悩む
    0.91
    Activations Density 0.098%

    No Known Activations