© 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. 10-GEMMASCOPE-RES-131K
    7. 86262
    Prev
    Next
    INDEX
    Explanations

    numpy

    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
    ).
    -2.09
    })
    -1.82
    晅
    -1.80
    ፨
    -1.77
    了两
    -1.77
    譬
    -1.75
     a
    -1.73
     utilizzando
    -1.70
    ’,
    -1.66
    ."
    -1.63
    POSITIVE LOGITS
     IBRARY
    1.76
    쑨
    1.68
    
    1.66
    
    1.62
     墊
    1.56
     beter
    1.55
    鑁
    1.53
     BRARY
    1.52
     hvilken
    1.51
     asma
    1.49
    Activations Density 0.005%

    No Known Activations