© 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. 35028
    Prev
    Next
    INDEX
    Explanations

    image rights and permission

    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
     assisted
    -1.04
    ]=='
    -1.03
    -//
    -1.01
    DTOs
    -1.01
    囔
    -1.00
    }`,
    -0.99
    ดู
    -0.98
     aid
    -0.98
     assistance
    -0.96
    骶
    -0.96
    POSITIVE LOGITS
     copyright
    1.35
     originaux
    1.15
     licensing
    1.15
     copyrights
    1.12
     copyrighted
    1.05
     rights
    1.02
     royalty
    1.01
     katk
    1.00
    的笑
    1.00
     royalties
    0.99
    Activations Density 0.046%

    No Known Activations