© 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. 10-GEMMASCOPE-RES-131K
    7. 57544
    Prev
    Next
    INDEX
    Explanations

    diagnostics, Gregg, ZX Spectrum

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

    The neuron strongly activates on occurrences of the word “diagnostics” (and closely related technical‐term tokens) in a document.

    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
    л
    -2.53
    </u>
    -2.50
    你看
    -2.44
    媗
    -2.42
    0
    -2.41
    嫫
    -2.36
    咦
    -2.30
    en
    -2.30
    ܜ
    -2.30
    艫
    -2.28
    POSITIVE LOGITS
    ’
    4.19
    等等
    2.27
     Durchmesser
    2.25
    s
    2.25
     sabid
    2.23
    prong
    2.23
     něj
    2.20
     樓
    2.17
     ؛
    2.11
    大帝
    2.09
    Activations Density 0.013%

    No Known Activations