© 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. 22-GEMMASCOPE-RES-131K
    7. 27133
    Prev
    Next
    INDEX
    Explanations

    equipment, AWS, body parts, disruption at, consumers to, pouches for

    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
    Polska
    -1.14
    闍
    -1.07
     TableColumn
    -1.05
    得太
    -1.05
     Θε
    -1.03
    США
    -1.01
    𝐊
    -1.00
     jButton
    -0.99
     onItemClick
    -0.98
    入了
    -0.96
    POSITIVE LOGITS
     jų
    1.02
     thier
    1.02
    êle
    0.93
    IZACIÓN
    0.89
    ÍST
    0.88
    ㄉ
    0.88
    óticas
    0.88
     lembra
    0.86
     materiałów
    0.83
    btnLogin
    0.83
    Activations Density 0.112%

    No Known Activations