© 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. 13889
    Prev
    Next
    INDEX
    Explanations

    you and yourself

    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
    -1.23
     today
    -1.22
     our
    -1.09
     would
    -1.05
    IFUL
    -1.04
     this
    -1.03
     환
    -1.03
    ริง
    -1.01
    すぎる
    -1.01
     unserer
    -1.01
    POSITIVE LOGITS
     your
    2.56
     you
    2.44
     yourself
    2.05
    你
    1.55
    当你
    1.49
     musíte
    1.33
    diğiniz
    1.25
     certain
    1.16
     máte
    1.16
    manız
    1.14
    Activations Density 0.075%

    No Known Activations