© 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. 95783
    Prev
    Next
    INDEX
    Explanations

    URLs to technical documentation

    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
    bieter
    -1.34
    máy
    -1.27
     časti
    -1.26
    了不少
    -1.24
    prada
    -1.20
     izman
    -1.20
    śni
    -1.16
    ݯ
    -1.16
     tikra
    -1.16
     jį
    -1.13
    POSITIVE LOGITS
    or
    1.21
     is
    1.14
     fusca
    1.13
    which
    1.12
    en
    1.12
    ed
    1.10
    elerik
    1.08
    s
    1.08
    ValueGeneration
    1.06
    ва
    1.05
    Activations Density 0.015%

    No Known Activations