© 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. 16758
    Prev
    Next
    INDEX
    Explanations

    base url or root url

    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
     Ohren
    -1.14
     alcune
    -1.10
     связанные
    -1.10
     Aussehen
    -1.10
    聍
    -1.09
    mme
    -1.02
    aed
    -1.00
     CLAIMS
    -0.99
    ğun
    -0.98
     ina
    -0.98
    POSITIVE LOGITS
    Despite
    1.26
    Although
    1.26
     komunikasi
    1.20
    For
    1.19
     for
    1.15
    Even
    1.13
    質問
    1.13
    极了
    1.11
    Without
    1.11
    From
    1.09
    Activations Density 0.018%

    No Known Activations