© 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. 39747
    Prev
    Next
    INDEX
    Explanations

    computer files stored on computer

    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
     with
    -0.97
    sourceMap
    -0.97
     زیرا
    -0.97
    mbing
    -0.95
     others
    -0.95
    باشد
    -0.95
     الثاني
    -0.92
    комнат
    -0.92
    瞧
    -0.91
    ил
    -0.91
    POSITIVE LOGITS
     Профиль
    1.27
     your
    1.23
     概要
    1.20
    сятся
    1.19
    zieht
    1.19
     obiet
    1.19
    ПРИ
    1.15
    telep
    1.14
    Чтоб
    1.14
     permett
    1.13
    Activations Density 0.014%

    No Known Activations