© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72707
    Prev
    Next
    INDEX
    Explanations

    data organization and quality

    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
     but
    -1.41
     namun
    -1.29
     ‘
    -1.24
     encaps
    -1.16
    ramid
    -1.15
    三个
    -1.14
    ्यो
    -1.14
    웠
    -1.13
    没有
    -1.09
    BorderSize
    -1.08
    POSITIVE LOGITS
     it
    1.66
     sarili
    1.41
     rhein
    1.36
    これに
    1.28
    他にも
    1.26
    快速的
    1.21
     silang
    1.20
     oxu
    1.19
     tanong
    1.19
     jota
    1.18
    Activations Density 0.275%

    No Known Activations