© 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. 34025
    Prev
    Next
    INDEX
    Explanations

    legal contexts and specific entities

    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
     this
    -1.94
     блюдо
    -1.55
     that
    -1.48
    ἵ
    -1.33
     LIABLE
    -1.27
     religieux
    -1.27
     минера
    -1.23
    喊道
    -1.20
     there
    -1.19
     kutoka
    -1.19
    POSITIVE LOGITS
    וּ
    1.68
    ִּ
    1.63
    ּוֹ
    1.60
    ̳
    1.41
    ַּ
    1.39
    动静
    1.35
    Inggris
    1.34
    توضیحات
    1.34
     litigation
    1.31
    ándolos
    1.30
    Activations Density 0.031%

    No Known Activations