© 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. 98229
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming contexts

    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
    確認ください
    -0.97
    か月
    -0.88
     湾
    -0.87
    쌉
    -0.86
     podrob
    -0.84
     informací
    -0.84
     nejak
    -0.83
    Один
    -0.83
     votación
    -0.83
     operands
    -0.82
    POSITIVE LOGITS
     Wikipedia
    0.82
     می‌گو
    0.79
     formal
    0.78
    lllllll
    0.77
    LLL
    0.76
    //{
    0.75
    صاص
    0.75
    エ
    0.75
     it
    0.73
     Kraj
    0.73
    Activations Density 0.048%

    No Known Activations