© 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. 15522
    Prev
    Next
    INDEX
    Explanations

    majority of

    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
     distintos
    -2.25
     diversos
    -2.22
    érieurs
    -2.20
    ↵↵
    -2.19
     nová
    -2.11
     большим
    -2.08
     素人
    -2.06
     trabajadores
    -2.03
     diferentes
    -2.02
     çeşitli
    -2.02
    POSITIVE LOGITS
     of
    3.50
    趼
    2.34
    Ꭳ
    2.19
     peines
    2.16
    本日の
    2.11
    鈈
    2.11
     gruppe
    2.09
    现在的
    2.09
     etek
    2.08
     शुर
    2.06
    Activations Density 0.014%

    No Known Activations