© 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. 93199
    Prev
    Next
    INDEX
    Explanations

    academic writing and theses

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

    The neuron fires most strongly on academic‐writing vocabulary (terms like “writing,” “research,” “thesis,” “skills,” “Communications,” 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_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
    ariums
    -1.32
    tablissements
    -1.27
     творо
    -1.21
     ilustrasi
    -1.14
     estrictamente
    -1.13
     detalló
    -1.08
     people
    -1.07
     ū
    -1.05
     ハンドメイド
    -1.05
    figcaption
    -1.04
    POSITIVE LOGITS
     your
    1.42
     writing
    1.29
    getProject
    1.27
     cristianismo
    1.26
     students
    1.23
    🆚
    1.20
     conseillé
    1.18
     čes
    1.17
     öğren
    1.16
    leuchte
    1.16
    Activations Density 0.030%

    No Known Activations