© 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. 25146
    Prev
    Next
    INDEX
    Explanations

    arXiv, patent, application links

    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
    They
    -1.84
     Therefore
    -1.77
    These
    -1.71
    That
    -1.57
    How
    -1.49
    Also
    -1.49
    It
    -1.48
     say
    -1.45
     The
    -1.45
    There
    -1.42
    POSITIVE LOGITS
    鲮
    1.41
     feit
    1.41
    妧
    1.39
    锵
    1.36
    TRIBUTION
    1.34
    不错的
    1.33
     звезда
    1.32
     bientôt
    1.30
    叹息
    1.30
    ⵌ
    1.30
    Activations Density 0.004%

    No Known Activations