© 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. 33083
    Prev
    Next
    INDEX
    Explanations

    code definition keywords

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

    This neuron specializes in spotting Python decorator names (identifiers appearing after an “@” in code).

    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
     whereas
    -1.14
     finally
    -1.10
    ;
    -1.09
    んでも
    -1.06
    cobs
    -1.02
    を使用して
    -1.02
    ).
    -1.01
     mentre
    -0.96
    two
    -0.94
    җ
    -0.91
    POSITIVE LOGITS
     cualquier
    1.32
     deliciosos
    1.27
    Informasi
    1.20
    Belum
    1.20
     coger
    1.19
    Jawab
    1.17
    Waktu
    1.16
    初め
    1.16
    Penjelasan
    1.13
     personagens
    1.13
    Activations Density 0.004%

    No Known Activations