© 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. 65544
    Prev
    Next
    INDEX
    Explanations

    phrase connectors after 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
     géant
    -1.42
     tatuajes
    -1.31
     enää
    -1.22
     Asegúrese
    -1.20
     diverses
    -1.20
    varios
    -1.20
     sandalias
    -1.19
     Frankrijk
    -1.18
    tuvo
    -1.17
    靼
    -1.15
    POSITIVE LOGITS
     while
    2.48
     from
    2.44
     and
    1.88
     including
    1.85
     regardless
    1.75
    while
    1.69
     without
    1.65
     whether
    1.52
     allowing
    1.51
     helping
    1.48
    Activations Density 0.077%

    No Known Activations