© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98208
    Prev
    Next
    INDEX
    Explanations

    code snippets ending with 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
     Februari
    -0.97
    🙋
    -0.88
    ғы
    -0.88
    outState
    -0.87
     किताब
    -0.85
    sth
    -0.82
    DataStore
    -0.81
     dvi
    -0.80
     Zing
    -0.79
    оны
    -0.77
    POSITIVE LOGITS
     невозможно
    0.84
     empêcher
    0.83
     Immune
    0.80
     skip
    0.77
     unable
    0.77
     proceed
    0.76
     nimmt
    0.76
     nahmen
    0.76
    Proceed
    0.75
     नहीं
    0.74
    Activations Density 0.018%

    No Known Activations