© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11885
    Prev
    Next
    INDEX
    Explanations

    defining lists of items

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

    This neuron responds strongly to rare or outlier tokens—uncommon words or names that stand out from the surrounding text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    времен
    0.81
    ш
    0.77
    ма
    0.73
    asını
    0.72
    у
    0.72
    рти
    0.70
    n
    0.68
    в
    0.68
    триму
    0.68
     মরি
    0.67
    POSITIVE LOGITS
     levar
    1.09
     DeConcini
    1.04
     española
    1.03
     quebr
    0.91
     chegar
    0.90
     AEW
    0.90
     estadounidense
    0.89
     daqui
    0.89
     dicho
    0.89
     extravag
    0.89
    Activations Density 0.000%

    No Known Activations