© 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. 13071
    Prev
    Next
    INDEX
    Explanations

    equally followed by descriptor

    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
     Publikum
    -1.67
    damento
    -1.66
     dasarnya
    -1.65
     Konflikt
    -1.53
     跳转至
    -1.52
     Consistent
    -1.51
     since
    -1.50
    gements
    -1.48
    vmware
    -1.47
    enegger
    -1.46
    POSITIVE LOGITS
    注意事
    1.70
    
    1.66
    n
    1.64
     knows
    1.61
    licitud
    1.55
     メモ
    1.52
     pureza
    1.50
    却又
    1.44
    }
    1.43
    赁
    1.43
    Activations Density 0.006%

    No Known Activations