© 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. 118196
    Prev
    Next
    INDEX
    Explanations

    numbers and 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_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
     RIM
    -0.72
     postres
    -0.71
    ਸ਼
    -0.71
    BMS
    -0.71
    Synopsis
    -0.71
    creation
    -0.69
     Transvaal
    -0.68
     Lala
    -0.67
    haya
    -0.66
     chay
    -0.66
    POSITIVE LOGITS
     NSError
    0.71
     جمع
    0.71
    olson
    0.70
    kett
    0.66
    multi
    0.65
     peł
    0.64
     Manager
    0.63
     réus
    0.63
     mét
    0.62
     Custom
    0.61
    Activations Density 0.064%

    No Known Activations