© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28486
    Prev
    Next
    INDEX
    Explanations

    fetching next element

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

    The main thing this neuron does is detect calls to advancing‐or‐retrieval methods (e.g. next(), Read(), FETCH NEXT) that move to or return the next element in an iterator/stream.

    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
     to
    -1.27
     “
    -1.08
    tipp
    -0.98
     apenas
    -0.94
    op
    -0.94
    NOX
    -0.92
     incluso
    -0.90
    contentValues
    -0.90
    -};
    -0.90
     IActionResult
    -0.90
    POSITIVE LOGITS
    ższych
    1.48
    During
    1.37
    omyelitis
    1.36
    miques
    1.31
     herido
    1.31
    的问道
    1.27
    Since
    1.24
     Undoubtedly
    1.23
     dår
    1.22
     enfermo
    1.21
    Activations Density 0.001%

    No Known Activations