© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68066
    Prev
    Next
    INDEX
    Explanations

    areas for improvement

    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
    Become
    -1.43
     mulus
    -1.40
    🏃
    -1.37
    𝑅
    -1.35
     руке
    -1.34
    )　
    -1.34
     perpé
    -1.31
     déjeuner
    -1.31
     idee
    -1.30
     cuillère
    -1.30
    POSITIVE LOGITS
     that
    2.39
     which
    1.57
     such
    1.46
    tagena
    1.45
     następnie
    1.41
     where
    1.39
    Problemas
    1.38
     possib
    1.38
     todays
    1.34
     spru
    1.30
    Activations Density 0.027%

    No Known Activations