© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40949
    Prev
    Next
    INDEX
    Explanations

    short-lived and long-lived

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

    The neuron fires on past‐participle adjective stems—particularly the “lived” in “short-lived”/“long-lived” and the “borne” in “arthropod-borne,” i.e. words 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_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
    抬手
    -2.48
    转头
    -2.27
    そういえば
    -2.19
    低声
    -2.09
     Ausrüstung
    -2.09
    聽到
    -1.99
     bessere
    -1.97
    钏
    -1.96
    menina
    -1.96
    をもら
    -1.95
    POSITIVE LOGITS
     –
    2.14
     brauche
    2.14
    m
    2.13
    		
    2.13
    、
    2.09
    ;
    2.06
    𞤢
    2.06
    。
    1.98
    !");
    1.98
     These
    1.92
    Activations Density 0.006%

    No Known Activations