© 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. 70542
    Prev
    Next
    INDEX
    Explanations

    analyses, studies, and outcomes

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

    The neuron fires on key scholarly or methodological nouns (e.g. “process,” “strategy,” “factor,” “impact,” “difference,” “study,” “analysis”) that label research concepts or steps.

    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
     and
    -1.23
     one
    -1.11
     not
    -1.11
     or
    -1.08
     facilitate
    -1.06
     wholly
    -1.05
     decreased
    -1.04
     facilitates
    -1.03
     multifaceted
    -1.02
     facilitating
    -1.00
    POSITIVE LOGITS
     of
    1.38
     ſeveral
    1.08
     Evaluación
    1.05
     sumptuous
    1.02
    柔らかい
    1.02
     tumultuous
    1.01
    certainly
    1.00
    ꔹ
    1.00
     Función
    1.00
     delightful
    1.00
    Activations Density 0.130%

    No Known Activations