© 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. 9740
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    This neuron activates on academic-style inline citation markers (e.g. “[number]”).

    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
     бампер
    -1.22
    日を
    -1.06
    ּוֹ
    -1.05
    레스
    -1.02
    lük
    -1.02
     trabajos
    -0.98
     descendre
    -0.98
     reposer
    -0.96
     niebies
    -0.96
     बताया
    -0.96
    POSITIVE LOGITS
    谙
    1.33
    vét
    1.14
    udz
    1.13
     péro
    1.11
     maquina
    1.10
     blusas
    1.09
     corrom
    1.08
    世上
    1.05
     bahkan
    1.04
     szczególnie
    1.04
    Activations Density 0.001%

    No Known Activations