© 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. 32772
    Prev
    Next
    INDEX
    Explanations

    enumerations of quantities

    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
     that
    -1.52
     even
    -1.42
     its
    -1.31
    Even
    -1.25
     the
    -1.18
    Both
    -1.13
     where
    -1.12
     Even
    -1.12
     it
    -1.10
    Other
    -1.10
    POSITIVE LOGITS
    mohon
    1.23
     kaksi
    1.12
    OTES
    1.04
     cuatro
    1.04
     ثلاثة
    1.01
    将在
    0.98
    乐趣
    0.96
     fyra
    0.96
    Publik
    0.93
     државе
    0.92
    Activations Density 0.046%

    No Known Activations