© 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. 22-GEMMASCOPE-RES-131K
    7. 34213
    Prev
    Next
    INDEX
    Explanations

    optimization and fitting algorithms

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

    The neuron activates on technical terms related to optimization and iterative algorithmic schemes (e.g. “iterative,” “optimization,” “fitting,” “objective,” “scheme”).

    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
     сих
    -1.21
     expan
    -1.07
    劃
    -1.05
    parentElement
    -0.98
     koi
    -0.96
    

    -0.96
    Ak
    -0.95
    ﺅ
    -0.95
    した場合
    -0.94
    離開
    -0.94
    POSITIVE LOGITS
     find
    1.18
    ӥ
    1.11
     with
    1.09
     or
    1.08
    〜
    1.05
     using
    1.04
    kräf
    1.04
     compéti
    1.00
     bekämp
    1.00
     nyel
    0.99
    Activations Density 0.037%

    No Known Activations