© 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. 116750
    Prev
    Next
    INDEX
    Explanations

    iterative reconstruction and completion

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

    The neuron fires on technical method keywords and modifiers (e.g. “improved,” “iterative,” “quantitative,” “compressed,” “analytic”) used to describe algorithmic or reconstruction techniques in scientific writing.

    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
    romycin
    -0.79
    reportError
    -0.76
    jske
    -0.73
     disallowed
    -0.73
    zić
    -0.72
     discriminant
    -0.72
     gesprek
    -0.71
     auftreten
    -0.71
    лим
    -0.69
    питан
    -0.69
    POSITIVE LOGITS
    gridx
    0.86
     proximal
    0.82
     prox
    0.81
    沾
    0.79
     operators
    0.79
     fft
    0.79
     Oldenburg
    0.79
    гают
    0.79
     accelerated
    0.78
    回去
    0.77
    Activations Density 0.024%

    No Known Activations