© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 268
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    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_34/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
     sonriente
    -1.49
     kolejny
    -1.33
    ﱠ
    -1.26
    を行い
    -1.25
     други
    -1.23
     maravillosa
    -1.22
     według
    -1.20
     acoged
    -1.19
     cómoda
    -1.15
    २
    -1.14
    POSITIVE LOGITS
     💜
    1.30
     ♥️
    1.27
     🥳
    1.23
     💗
    1.22
     ❤
    1.22
     💛
    1.20
    although
    1.18
     ✌
    1.18
     belf
    1.17
     🥰
    1.16
    Activations Density 0.018%

    No Known Activations