© 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. 34-GEMMASCOPE-RES-131K
    7. 111084
    Prev
    Next
    INDEX
    Explanations

    container or storage

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

    This neuron detects declaration‐introducing keywords in code—words like “def,” “val,” “class,” “template,” “struct,” “typedef,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    pausal
    -0.84
    jaga
    -0.82
     individuo
    -0.82
     revisit
    -0.82
     segundo
    -0.79
    )):
    -0.79
    chke
    -0.77
    estay
    -0.76
     konu
    -0.75
     resultado
    -0.74
    POSITIVE LOGITS
     storage
    1.28
     contents
    1.26
     data
    1.18
     backing
    1.14
    data
    1.14
     underlying
    1.13
     datastore
    1.11
    Backing
    1.09
     content
    1.05
    storage
    1.05
    Activations Density 0.050%

    No Known Activations