© 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. 39421
    Prev
    Next
    INDEX
    Explanations

    multilingual text components

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

    The neuron is spotting past‐participle (–ed) verb forms (i.e. tokens ending in “ed”).

    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
     —
    -1.30
    </em>
    -1.05
    ,
    -1.04
    mar
    -1.01
    </i>
    -1.00
     will
    -0.97
     would
    -0.95
    it
    -0.95
     UPON
    -0.94
    de
    -0.93
    POSITIVE LOGITS
     tristes
    1.21
    Terima
    1.16
    Spesifikasi
    1.05
    JAJA
    1.03
    ſten
    1.03
    Pengertian
    1.00
    IALE
    1.00
    iziert
    0.97
    Clic
    0.97
    ITURE
    0.96
    Activations Density 0.015%

    No Known Activations