© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68236
    Prev
    Next
    INDEX
    Explanations

    programming output and logging

    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_22/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
     including
    -1.13
     include
    -1.06
     what
    -1.06
     deliberately
    -1.04
     các
    -1.04
     if
    -1.02
     non
    -1.02
     with
    -1.02
     new
    -1.01
     people
    -1.00
    POSITIVE LOGITS
    -------
    1.27
    ジェクト
    1.18
    <>
    1.13
     accesible
    1.12
     ähnliche
    1.12
     sạc
    1.10
     kleinere
    1.09
     disting
    1.08
     firft
    1.08
     ballon
    1.08
    Activations Density 0.003%

    No Known Activations