© 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. 36511
    Prev
    Next
    INDEX
    Explanations

    player changes or substitutes

    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
     פשוט
    -1.12
     tôt
    -0.97
    often
    -0.88
    laş
    -0.88
     объект
    -0.87
    zca
    -0.85
    uſ
    -0.85
     garantit
    -0.84
     française
    -0.82
     कीजिए
    -0.82
    POSITIVE LOGITS
     additional
    1.23
     substitutes
    1.06
    قرأ
    1.05
     substitute
    1.05
     changes
    1.03
     change
    1.00
    :"",
    0.99
    inkov
    0.97
    替换
    0.96
    ínico
    0.96
    Activations Density 0.002%

    No Known Activations