© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    string concatenation with `+`

    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
     Those
    -1.48
     if
    -1.45
    Those
    -1.41
     with
    -1.33
     establishes
    -1.32
     establishing
    -1.29
     sehr
    -1.29
     those
    -1.27
     bringing
    -1.27
     this
    -1.26
    POSITIVE LOGITS
     delightful
    1.57
     terrific
    1.49
     myriad
    1.45
     gigantic
    1.45
    </b>
    1.41
     marvelous
    1.39
     goofy
    1.34
     wonderful
    1.32
     antiguos
    1.32
     magnificent
    1.31
    Activations Density 0.002%

    No Known Activations