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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54226
    Prev
    Next
    INDEX
    Explanations

    ages of children and babies

    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
     /
    -1.16
     !
    -1.02
    男友
    -1.00
    でも
    -0.99
    områ
    -0.96
    sterreich
    -0.96
    ׇ
    -0.96
     more
    -0.94
     sebagaimana
    -0.94
     sayesinde
    -0.93
    POSITIVE LOGITS
    ַּ
    1.34
    ּוֹ
    1.24
    ?></
    1.15
    ditionally
    1.11
     السياس
    1.10
     two
    1.09
    　　　　　　
    1.08
     efektif
    1.07
    })();
    1.06
     две
    1.01
    Activations Density 0.024%

    No Known Activations