© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15442
    Prev
    Next
    INDEX
    Explanations

    retrieve parameter or attribute

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

    The neuron consistently fires on occurrences of “get” in code—i.e. getter or retrieval method names and calls.

    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
    也在
    -1.27
     and
    -1.22
    t
    -1.17
    和
    -1.13
     immediately
    -1.09
     anderen
    -1.05
     Freiw
    -1.04
    已经
    -1.03
    amatkan
    -1.02
    文化
    -1.00
    POSITIVE LOGITS
    囔
    1.43
    девушка
    1.36
    alors
    1.34
    bước
    1.34
     nélkül
    1.34
    ==
    1.31
    																														
    1.30
    ڰ
    1.27
    mientras
    1.27
    quivado
    1.26
    Activations Density 0.001%

    No Known Activations