© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64910
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -1.69
     even
    -1.54
     with
    -1.53
     of
    -1.44
     only
    -1.43
     from
    -1.40
     have
    -1.29
     just
    -1.26
     has
    -1.21
     its
    -1.20
    POSITIVE LOGITS
    取决
    1.41
     reemplazar
    1.26
     asegur
    1.23
    Lø
    1.20
    极为
    1.20
    biendo
    1.18
     остался
    1.18
     réparer
    1.17
     можем
    1.17
    forcing
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.