© 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. 12593
    Prev
    Next
    INDEX
    Explanations

    quoted or enclosed words

    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
    贋
    -1.42
     веке
    -1.40
    against
    -1.30
     (
    -1.29
     розовый
    -1.27
     limpiar
    -1.26
     TÉ
    -1.24
    媗
    -1.22
     japonais
    -1.22
     vermelha
    -1.22
    POSITIVE LOGITS
    atação
    1.27
    Boxscore
    1.23
    Adverten
    1.20
     ❤
    1.19
    УДК
    1.18
     &.
    1.16
     weshalb
    1.15
    Transk
    1.14
     شیپور
    1.13
    Приготовление
    1.13
    Activations Density 0.028%

    No Known Activations