© 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. 33413
    Prev
    Next
    INDEX
    Explanations

    class definitions and object access

    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
    Not in Any Lists

    No Comments

    Negative Logits
     rendent
    -1.09
     ["",
    -1.09
     getroffen
    -1.09
    етесь
    -1.02
     $(".
    -1.02
     tiennent
    -1.00
     réservoir
    -1.00
     تلك
    -1.00
    これらの
    -0.99
     quatrième
    -0.99
    POSITIVE LOGITS
     name
    1.18
     also
    1.18
     got
    1.16
     had
    1.13
     потом
    1.11
     has
    1.10
     is
    1.10
     technology
    1.09
     responsible
    1.08
     display
    1.07
    Activations Density 0.019%

    No Known Activations