© 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. 129037
    Prev
    Next
    INDEX
    Explanations

    whole [noun]

    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
     detenidos
    -1.09
     dois
    -1.07
    Эзоҳ
    -1.06
     heridos
    -1.04
    얄
    -1.00
    它的
    -0.94
     giorni
    -0.94
     ganadores
    -0.93
    了两
    -0.93
    蒸し
    -0.91
    POSITIVE LOGITS
    ضير
    1.13
    曏
    1.08
     közül
    1.05
     inoltre
    1.04
    autoreleasepool
    1.03
    lcccccc
    1.02
    
    1.01
     Pleasant
    1.01
     different
    1.00
    EDS
    0.98
    Activations Density 0.022%

    No Known Activations