© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60813
    Prev
    Next
    INDEX
    Explanations

    newspaper 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_10/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
     persönlichen
    -1.52
     ersten
    -1.38
     abiertos
    -1.36
     them
    -1.27
    зависи
    -1.25
     allgemeinen
    -1.24
     อย
    -1.23
    噲
    -1.20
    久しぶり
    -1.20
     когда
    -1.19
    POSITIVE LOGITS
    ↵↵↵↵↵
    1.30
    M
    1.20
    之处
    1.20
     seines
    1.16
     in
    1.13
     brach
    1.13
    เทพ
    1.12
     видит
    1.11
    "">
    1.09
    )){
    1.09
    Activations Density 0.020%

    No Known Activations