© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 98800
    Prev
    Next
    INDEX
    Explanations

    clarify, confirm, recap, record

    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
    Negative Logits
     and
    -1.34
    Their
    -1.30
    他们
    -1.24
    Why
    -1.18
    Still
    -1.17
    他們
    -1.16
    They
    -1.15
     Если
    -1.13
    ᾱ
    -1.11
     مختلف
    -1.10
    POSITIVE LOGITS
    还不错
    1.41
     faible
    1.23
    回到了
    1.20
    .='
    1.19
    描く
    1.18
    missible
    1.16
     покупать
    1.15
    ()}>
    1.13
    様に
    1.13
    ínio
    1.13
    Activations Density 0.067%

    No Known Activations