© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93391
    Prev
    Next
    INDEX
    Explanations

    colors and code

    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
    existsSync
    -1.33
    %;
    
    -1.27
     hongos
    -1.25
    queryInterface
    -1.24
    ּוֹ
    -1.16
    AfterViewInit
    -1.16
    ksis
    -1.13
    inflater
    -1.13
    subsubsection
    -1.13
     him
    -1.13
    POSITIVE LOGITS
     اللون
    1.13
    getreten
    1.13
     botanique
    1.12
     anklicken
    1.05
     黑色
    1.04
     palettes
    1.02
     رنگی
    1.02
     pablo
    1.02
     isEqual
    1.02
     that
    1.02
    Activations Density 0.034%

    No Known Activations