© 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. 26023
    Prev
    Next
    INDEX
    Explanations

    relative pronouns followed by verbs

    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
     was
    -1.52
     sarà
    -1.24
     **/
    -1.13
     is
    -1.12
     mentre
    -1.09
     wasn
    -1.08
    了一种
    -1.08
     creato
    -1.02
    是个
    -1.02
     sogar
    -1.02
    POSITIVE LOGITS
     are
    1.50
     έχουν
    1.39
    Inggris
    1.27
     have
    1.27
     často
    1.26
     przecież
    1.26
     vannak
    1.17
     menikah
    1.15
    を選択します
    1.15
    yoruz
    1.12
    Activations Density 0.134%

    No Known Activations