© 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. 22-GEMMASCOPE-RES-131K
    7. 24899
    Prev
    Next
    INDEX
    Explanations

    designed for purpose

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     when
    -1.46
     before
    -1.31
    <bos>
    -1.31
     áreas
    -1.27
    Encontra
    -1.23
    Produkte
    -1.20
    够了
    -1.19
    来源于
    -1.16
    íticos
    -1.15
     sốt
    -1.13
    POSITIVE LOGITS
     to
    3.39
     כך
    1.37
     that
    1.37
    حيث
    1.20
     particolare
    1.20
    ariana
    1.14
    thul
    1.13
    えっ
    1.13
     
    1.12
    様に
    1.11
    Activations Density 0.069%

    No Known Activations