© 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. 66454
    Prev
    Next
    INDEX
    Explanations

    Joomla components

    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
    étit
    -1.59
    ține
    -1.53
     był
    -1.46
     був
    -1.43
     oef
    -1.38
    力
    -1.37
     trouw
    -1.35
     czarna
    -1.35
    久しぶり
    -1.31
     buvo
    -1.30
    POSITIVE LOGITS
     between
    1.45
    我了
    1.42
    മാ
    1.39
    其实是
    1.37
    не
    1.34
    銣
    1.30
     &
    1.27
     materiału
    1.27
     beginnt
    1.26
    *)&
    1.23
    Activations Density 0.015%

    No Known Activations