© 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. 34-GEMMASCOPE-RES-131K
    7. 49294
    Prev
    Next
    INDEX
    Explanations

    as published by

    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_34/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
     accordance
    -1.04
     zupeł
    -1.01
     menurut
    -0.97
     neceffary
    -0.94
    計画
    -0.94
     encouraged
    -0.94
    使って
    -0.91
     instructed
    -0.90
     caufe
    -0.90
     emplea
    -0.90
    POSITIVE LOGITS
     as
    1.44
     amended
    1.30
     اندروید
    1.22
    modified
    1.02
    tainable
    0.99
    อ่าน
    0.94
     modified
    0.94
     unmodified
    0.94
     tirs
    0.93
    Tikang
    0.92
    Activations Density 0.061%

    No Known Activations