© 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. 14845
    Prev
    Next
    INDEX
    Explanations

    REFERENCES

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

    The neuron fires on numeric reference markers or citation indices (e.g. bracketed or standalone numbers used for citations and footnotes).

    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
    Untuk
    -1.29
     também
    -1.06
     みた
    -1.05
    Также
    -1.05
    Selain
    -1.02
    würdigkeiten
    -0.97
    mohon
    -0.97
     will
    -0.95
     تبد
    -0.95
     needed
    -0.94
    POSITIVE LOGITS
         
    1.12
    pagnes
    1.04
    ">)</
    1.02
    rotter
    1.02
     statistique
    1.00
    勇者
    0.99
    ]=\
    0.98
    ето
    0.98
           
    0.97
    0.96
    Activations Density 0.002%

    No Known Activations