© 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. 129166
    Prev
    Next
    INDEX
    Explanations

    forms, requests, and services

    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
     our
    -1.62
     we
    -1.55
     Erzb
    -1.54
     ادبی
    -1.21
    ₅
    -1.17
     katholischen
    -1.16
     this
    -1.14
    alucía
    -1.12
    romeda
    -1.12
     ܐ
    -1.11
    POSITIVE LOGITS
    ּוֹ
    1.87
    וּ
    1.73
    Проце
    1.61
    וּ
    1.61
     procedure
    1.55
    ίη
    1.52
    וֹ
    1.46
    官员
    1.43
     process
    1.38
    FontAwesomeIcon
    1.38
    Activations Density 0.043%

    No Known Activations