© 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. 22-GEMMASCOPE-RES-131K
    7. 14198
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations

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

    The neuron strongly activates on long, multi‐syllable technical or domain-specific terms—particularly fragments of scientific journal names and other specialized vocabulary.

    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
     "
    -1.20
     you
    -1.19
    が終わ
    -1.17
    ...
    -1.15
    で一番
    -1.14
     one
    -1.10
    ."
    -1.09
     poniżej
    -1.09
     wüns
    -1.09
    salomon
    -1.07
    POSITIVE LOGITS
     rigide
    1.13
     transparentes
    1.13
    توضیحات
    1.09
    forder
    1.09
    ностей
    1.09
    ultimate
    1.08
    лыми
    1.08
    ahashi
    1.07
     majest
    1.06
    といいます
    1.06
    Activations Density 0.005%

    No Known Activations