© 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. 10-GEMMASCOPE-RES-131K
    7. 20450
    Prev
    Next
    INDEX
    Explanations

    sentence-ending 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_10/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
     absolut
    -1.63
    THERE
    -1.59
    attempts
    -1.59
    izmus
    -1.59
    äls
    -1.52
    端に
    -1.52
     rám
    -1.51
    র
    -1.48
     Мы
    -1.45
     😁
    -1.45
    POSITIVE LOGITS
     from
    1.79
     that
    1.70
     their
    1.63
     to
    1.63
    v
    1.53
     various
    1.46
     Since
    1.39
     mieć
    1.38
     getting
    1.38
     in
    1.37
    Activations Density 0.057%

    No Known Activations