© 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. 43524
    Prev
    Next
    INDEX
    Explanations

    EU, EC, Union, Europe

    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
     ส์
    -1.60
    ⚣
    -1.55
    䛗
    -1.53
    邂
    -1.52
    ⢅
    -1.52
     beliebtesten
    -1.51
     spolup
    -1.50
     bekämp
    -1.49
     wußte
    -1.43
    選ば
    -1.38
    POSITIVE LOGITS
    瑧
    1.77
    >
    1.59
     kvinna
    1.55
    ↵↵
    1.52
    】:
    1.52
    2
    1.50
    U
    1.49
    in
    1.45
     of
    1.43
     pamoja
    1.42
    Activations Density 0.022%

    No Known Activations