© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74501
    Prev
    Next
    INDEX
    Explanations

    X-ray non-destructive analysis and radiography

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

    The neuron is specialized for spotting occurrences of radiographic imaging terms (e.g. “neutron radiography,” “X‐ray radiography,” “dual‐energy X‐ray absorptiometry,” 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_10/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
     relata
    -1.34
     same
    -1.12
    来的
    -1.11
    周边
    -1.10
     gött
    -1.09
     augusti
    -1.09
    维持
    -1.07
    了一個
    -1.07
    unno
    -1.07
    。(
    -1.07
    POSITIVE LOGITS
    Another
    1.30
    ommer
    1.16
     zaterdag
    1.11
    mockMvc
    1.09
     минуты
    1.07
    ifico
    1.06
    bitkan
    1.05
    endaftar
    1.05
    一提
    1.04
    cení
    1.03
    Activations Density 0.181%

    No Known Activations