© 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. 39720
    Prev
    Next
    INDEX
    Explanations

    stopping punctuation

    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
     one
    -0.92
     absolutely
    -0.90
    험
    -0.88
     something
    -0.87
     any
    -0.84
     delivered
    -0.81
     all
    -0.79
     immediately
    -0.79
     препо
    -0.77
    üht
    -0.77
    POSITIVE LOGITS
     indicaciones
    0.93
     wzglę
    0.91
    そんなに
    0.91
    又不是
    0.91
    細かい
    0.90
     comté
    0.88
    んだよ
    0.88
    能不能
    0.87
    шины
    0.86
    чностью
    0.86
    Activations Density 0.019%

    No Known Activations