© 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. 101369
    Prev
    Next
    INDEX
    Explanations

    childhood and development

    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
     vicenda
    -1.28
     currently
    -1.09
    ᱾
    -1.08
    avez
    -1.05
    GRAFIA
    -1.03
    じゃあ
    -1.02
     satria
    -1.02
     velocità
    -1.02
     individuals
    -1.01
    asyarakat
    -1.01
    POSITIVE LOGITS
     väč
    1.54
     flesta
    1.34
    Descarga
    1.27
     meisten
    1.27
     ͡°)
    1.24
     که
    1.23
    ">//
    1.21
     semelhantes
    1.20
     crappy
    1.20
     információ
    1.20
    Activations Density 0.161%

    No Known Activations