© 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. 85885
    Prev
    Next
    INDEX
    Explanations

    abbreviations and proper names

    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
     mesto
    -1.18
     nueva
    -1.11
    ση
    -1.05
    ✁
    -1.05
     maestra
    -1.05
     mereka
    -1.04
     --
    -1.04
     nuevos
    -1.02
    ğiniz
    -1.01
    vants
    -1.00
    POSITIVE LOGITS
    ffl
    1.37
    complished
    1.18
     которы
    1.15
    訛
    1.12
    乃至
    1.11
    这边
    1.08
     who
    1.08
    curate
    1.07
    !"
    1.06
    (!__
    1.06
    Activations Density 0.338%

    No Known Activations