© 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. 10-GEMMASCOPE-RES-131K
    7. 13857
    Prev
    Next
    INDEX
    Explanations

    set method calls

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

    The neuron fires on occurrences of the substring “set” (often as part of setter method or function names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    皷
    -1.60
    彼らは
    -1.48
     they
    -1.41
     办
    -1.41
     was
    -1.38
     jeweiligen
    -1.31
    彼らの
    -1.30
    繾
    -1.28
    Zubereitung
    -1.28
     mereka
    -1.28
    POSITIVE LOGITS
    "
    1.63
    ↵
    1.47
     hare
    1.30
     ‘‘
    1.30
    in
    1.28
    тувати
    1.28
     galima
    1.26
    )
    1.23
    <0xE7>
    1.20
    ategori
    1.17
    Activations Density 0.008%

    No Known Activations