© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12309
    Prev
    Next
    INDEX
    Explanations

    died, killed, left

    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
    ﾟ)
    -1.06
     BEAR
    -1.02
     fön
    -1.01
     Nucl
    -0.97
    ometrics
    -0.96
     SCHEME
    -0.91
     bär
    -0.91
    retired
    -0.91
     backen
    -0.90
     offrent
    -0.90
    POSITIVE LOGITS
     his
    1.22
     replaced
    1.13
    留下
    1.02
     leaving
    1.00
     loved
    0.94
    เหลือ
    0.91
     hervorge
    0.86
     geprü
    0.85
     had
    0.84
     جس
    0.82
    Activations Density 0.084%

    No Known Activations