© 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. 22-GEMMASCOPE-RES-131K
    7. 26715
    Prev
    Next
    INDEX
    Explanations

    archive.fo or archive.is

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects mentions or URLs of web archive (archive.org) links, including related tokens in Chinese or English that refer to archived web pages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ruiter
    -1.13
    ↵↵
    -1.07
    entyfik
    -1.02
     oust
    -1.02
    ↵↵↵↵↵↵↵
    -1.00
    ]]=
    -1.00
    cektir
    -0.99
    renewable
    -0.97
    ↵↵↵↵↵↵↵↵↵↵
    -0.96
    blia
    -0.95
    POSITIVE LOGITS
     المختلفة
    1.13
    拍了拍
    0.97
     Теперь
    0.94
    当时的
    0.94
    讶
    0.93
     archived
    0.93
     témoignage
    0.91
    ȭ
    0.91
     from
    0.91
     carinho
    0.90
    Activations Density 0.025%

    No Known Activations