© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65965
    Prev
    Next
    INDEX
    Explanations

    verbs creating or presenting something

    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
     when
    -1.38
    đồ
    -1.27
    ִּ
    -1.25
    ませんか
    -1.16
     before
    -1.05
     because
    -1.03
     became
    -1.02
    尋找
    -1.02
     оно
    -1.02
    ingos
    -1.01
    POSITIVE LOGITS
     here
    1.35
     himself
    1.28
     レトロ
    1.06
     nėra
    1.05
    在这
    1.03
     THROUGH
    0.99
     Gestion
    0.99
    在他的
    0.96
     creat
    0.96
    creating
    0.95
    Activations Density 0.031%

    No Known Activations