© 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. 72203
    Prev
    Next
    INDEX
    Explanations

    picture or photo

    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
    }=\
    -1.61
    /*!
    -1.42
     Doesn
    -1.41
    也是
    -1.40
     and
    -1.39
    也不
    -1.35
    Также
    -1.35
     to
    -1.34
     While
    -1.33
    ,”
    -1.29
    POSITIVE LOGITS
     of
    1.75
    一張
    1.48
    一张
    1.47
    过去的
    1.43
    豪华
    1.34
     вещей
    1.34
    ❲
    1.30
    それと
    1.26
    怔
    1.25
    麻煩
    1.21
    Activations Density 0.062%

    No Known Activations