© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28265
    Prev
    Next
    INDEX
    Explanations

    object attribute access

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

    The neuron fires on programming identifiers (e.g. variable, function, class, or parameter names) 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
    を
    -1.39
     autres
    -1.16
     stessi
    -1.10
    これは
    -1.07
    や
    -1.05
    achter
    -1.04
     şun
    -1.04
    これも
    -1.04
    <bos>
    -1.04
    nasi
    -1.04
    POSITIVE LOGITS
     nélkül
    1.18
    着脸
    1.11
     található
    1.09
    łącz
    1.07
     képes
    1.06
     történ
    1.05
    ӏ
    1.03
     nélk
    1.02
     décembre
    1.01
     capaces
    1.01
    Activations Density 0.016%

    No Known Activations