© 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. 10-GEMMASCOPE-RES-131K
    7. 113009
    Prev
    Next
    INDEX
    Explanations

    spurious conclusions

    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_10/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
    蛻
    -2.75
    镚
    -2.64
    鉆
    -2.52
    瀏
    -2.52
    。『
    -2.50
    しようと
    -2.48
    錨
    -2.39
    ቬ
    -2.38
    しないと
    -2.38
    
    -2.36
    POSITIVE LOGITS
     "
    3.52
    ↵↵
    3.27
     
    2.98
     are
    2.67
     peuvent
    2.53
    在他
    2.52
     I
    2.48
     feita
    2.47
     --
    2.39
     charming
    2.36
    Activations Density 0.012%

    No Known Activations