© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90885
    Prev
    Next
    INDEX
    Explanations

    citations and descriptions

    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
     and
    -1.79
     when
    -1.66
     if
    -1.57
     out
    -1.53
     because
    -1.52
     with
    -1.48
    :][
    -1.39
     For
    -1.38
     việc
    -1.35
     jeśli
    -1.35
    POSITIVE LOGITS
    </b>
    1.73
     skak
    1.62
    了吧
    1.48
     maja
    1.46
    chläge
    1.39
     toppen
    1.38
     eene
    1.38
    我这
    1.36
     resten
    1.34
    ännande
    1.31
    Activations Density 0.013%

    No Known Activations