© 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. 115559
    Prev
    Next
    INDEX
    Explanations

    two to sequences of numbers

    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
    nine
    -0.78
    streifen
    -0.77
    9
    -0.76
    hundreds
    -0.73
    pions
    -0.72
    一九
    -0.72
    kissen
    -0.71
     getrock
    -0.69
    hrer
    -0.69
    islation
    -0.69
    POSITIVE LOGITS
     twice
    1.68
     Twice
    1.51
     two
    1.41
     Two
    1.34
     Два
    1.30
     zweimal
    1.27
    Twice
    1.26
     ۲
    1.17
    twice
    1.17
     два
    1.16
    Activations Density 0.068%

    No Known Activations