© 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. 40649
    Prev
    Next
    INDEX
    Explanations

    section or list item starts

    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
     bijvoorbeeld
    -1.45
     töö
    -1.42
    周りの
    -1.41
    他にも
    -1.37
    何より
    -1.35
    ieuse
    -1.27
    こども
    -1.27
    OTER
    -1.24
     nõ
    -1.24
     souvent
    -1.23
    POSITIVE LOGITS
     mengikut
    1.41
     with
    1.39
     iaitu
    1.36
     tumbuhan
    1.34
     espagnole
    1.26
     profondeur
    1.23
     selepas
    1.22
    .
    1.22
    lieving
    1.21
    från
    1.20
    Activations Density 0.009%

    No Known Activations