© 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. 9462
    Prev
    Next
    INDEX
    Explanations

    Russian, Ukrainian, Japanese, Spanish, Hindi, character names

    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
    ∅
    -1.16
     их
    -1.11
     to
    -1.09
     they
    -1.06
     Their
    -1.06
     każde
    -1.05
    Bbb
    -1.05
    ฿
    -1.05
     каждо
    -1.04
    łyn
    -1.04
    POSITIVE LOGITS
    <bos>
    1.42
    Zdrav
    1.36
     間取り
    1.29
    Evange
    1.20
    Зміст
    1.17
    Lindo
    1.17
    Характеристики
    1.16
    Vegeta
    1.16
    Подробнее
    1.15
    यह
    1.15
    Activations Density 0.022%

    No Known Activations