© 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. 75267
    Prev
    Next
    INDEX
    Explanations

    faith tried at times

    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
     unwavering
    -1.88
     unrelenting
    -1.77
     unusually
    -1.72
     if
    -1.72
     in
    -1.70
     =
    -1.69
     Typically
    -1.65
     Nearly
    -1.63
     after
    -1.59
    较为
    -1.59
    POSITIVE LOGITS
     fantastic
    1.89
    狨
    1.84
    mpagne
    1.84
    迨
    1.76
     reiter
    1.76
     seleccionados
    1.74
     流れ
    1.73
    硨
    1.73
    vacy
    1.70
     quando
    1.69
    Activations Density 0.001%

    No Known Activations