© 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. 20142
    Prev
    Next
    INDEX
    Explanations

    higher the value

    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
     all
    -1.30
     which
    -1.29
    :
    -1.27
    ipedi
    -1.23
    ENUM
    -1.18
    ner
    -1.13
    ames
    -1.11
    рити
    -1.11
    ak
    -1.09
    者的
    -1.09
    POSITIVE LOGITS
     häufiger
    1.34
     envió
    1.21
     dziś
    1.21
     mehrfach
    1.20
    śród
    1.19
    Bjs
    1.14
     gemeinsam
    1.12
     viaja
    1.11
    вла
    1.11
    是很
    1.09
    Activations Density 0.071%

    No Known Activations