© 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. 34-GEMMASCOPE-RES-131K
    7. 59318
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers or symbols

    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
     menatap
    -0.79
     ix
    -0.78
    Pep
    -0.77
    Hav
    -0.75
     Pep
    -0.74
    banded
    -0.73
     już
    -0.72
     Raffa
    -0.71
     Trần
    -0.71
     Hav
    -0.69
    POSITIVE LOGITS
    RICE
    0.79
    CEPTION
    0.77
    RECE
    0.76
    ៤
    0.72
     حب
    0.71
     FOURTH
    0.71
     Keyboard
    0.69
    триму
    0.69
    следования
    0.69
     коля
    0.69
    Activations Density 0.097%

    No Known Activations