© 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. 40070
    Prev
    Next
    INDEX
    Explanations

    conditional prefix `if` or `Q`

    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
     kimi
    -1.20
     dava
    -1.13
     ۲۰۰
    -1.09
     pasang
    -1.08
     murah
    -1.08
     spus
    -1.06
    wijl
    -1.04
     praktis
    -1.04
     utk
    -1.02
     pulsa
    -0.99
    POSITIVE LOGITS
     probabilmente
    1.30
    ถ้า
    1.09
    if
    1.08
     '(
    1.07
     darstellen
    1.06
    อาจ
    1.05
    了一眼
    1.04
    atization
    1.04
    }}(\
    1.04
     }}$
    1.04
    Activations Density 0.001%

    No Known Activations