© 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. 61021
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
    癀
    -3.03
    苤
    -2.58
    ⢪
    -2.48
     Dinas
    -2.22
    ጢ
    -2.19
    部分を
    -2.13
    𖣘
    -2.08
    ⎔
    -2.05
    removed
    -2.02
    ܞ
    -2.02
    POSITIVE LOGITS
     that
    2.89
     only
    2.69
     should
    2.67
     one
    2.63
     more
    2.41
    when
    2.38
     usually
    2.31
     it
    2.30
     Give
    2.28
     also
    2.27
    Activations Density 0.225%

    No Known Activations