© 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. 67163
    Prev
    Next
    INDEX
    Explanations

    ambassador, patron, honorary titles

    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
    自己的
    -1.09
     retrieve
    -1.00
    PhysRevD
    -1.00
    }}">
    -1.00
    à
    -0.97
    ౮
    -0.95
    type
    -0.95
    ={()=>
    -0.94
    टी
    -0.93
     viszont
    -0.92
    POSITIVE LOGITS
     of
    1.35
    嵙
    1.15
    Since
    1.12
    Several
    1.11
    Many
    1.08
     线条
    1.07
     resmi
    1.06
    goblin
    1.05
    According
    1.05
    campaigns
    1.05
    Activations Density 0.026%

    No Known Activations