© 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. 6062
    Prev
    Next
    INDEX
    Explanations

    variable names and code elements

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

    This neuron strongly fires on single‐word nouns serving as the direct object of a verb.

    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
    數學
    0.76
     vidéos
    0.75
     guidelines
    0.73
    ли
    0.72
    ㎿
    0.71
     bạc
    0.70
     sach
    0.69
    נ
    0.69
     sare
    0.68
     sä
    0.68
    POSITIVE LOGITS
    mensaje
    0.84
    teenth
    0.80
    Area
    0.80
    1
    0.80
     Steep
    0.79
    Rolling
    0.79
    Hospital
    0.79
    DropdownBox
    0.79
    Dec
    0.78
    Railway
    0.78
    Activations Density 0.000%

    No Known Activations