© 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. 801
    Prev
    Next
    INDEX
    Explanations

    linking clauses and listing

    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
    ︲
    -1.61
    횃
    -1.60
    ными
    -1.56
     savvy
    -1.50
    菒
    -1.49
     embellished
    -1.48
     molte
    -1.44
     depois
    -1.44
     ‌
    -1.43
     ścian
    -1.43
    POSITIVE LOGITS
     as
    2.14
     and
    1.93
     from
    1.78
     although
    1.73
     However
    1.73
     with
    1.59
     in
    1.58
    lardan
    1.49
    middag
    1.45
     oman
    1.44
    Activations Density 0.152%

    No Known Activations