© 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. 22-GEMMASCOPE-RES-131K
    7. 9591
    Prev
    Next
    INDEX
    Explanations

    trailing 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_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
     fortalec
    -1.35
    ighed
    -1.24
     necesar
    -1.24
     веке
    -1.24
    だったので
    -1.23
    FontAwesomeIcon
    -1.19
     akces
    -1.18
    alians
    -1.16
     Vergnügen
    -1.16
     esportes
    -1.15
    POSITIVE LOGITS
     also
    2.53
     furthermore
    1.49
     additionally
    1.47
     همچنین
    1.41
     moreover
    1.41
     your
    1.33
     plus
    1.32
     außerdem
    1.31
     dessutom
    1.30
     you
    1.26
    Activations Density 0.018%

    No Known Activations