© 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. 120022
    Prev
    Next
    INDEX
    Explanations

    sentence endings and list separators

    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
    糁
    -1.93
    ÑOS
    -1.76
     دانلود
    -1.70
     новым
    -1.67
     ſeveral
    -1.66
    Архівовано
    -1.65
    ままで
    -1.59
    iczny
    -1.53
    Eq
    -1.52
    Therefore
    -1.51
    POSITIVE LOGITS
     and
    1.88
     or
    1.71
    などと
    1.53
     but
    1.48
     cálculos
    1.36
     in
    1.34
     misschien
    1.32
     permitirá
    1.30
     might
    1.29
     if
    1.27
    Activations Density 0.006%

    No Known Activations