© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8302
    Prev
    Next
    INDEX
    Explanations

    video clip or location

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

    The neuron strongly activates on occurrences of the word “organization” (including its plural or related token forms).

    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
    Found
    0.71
    Fr
    0.63
    Sh
    0.61
    Vish
    0.61
    😍😍
    0.60
    found
    0.59
    Op
    0.58
    Liv
    0.57
    handel
    0.57
    Co
    0.56
    POSITIVE LOGITS
     perdre
    0.59
     неправи
    0.57
    贞
    0.55
     theirs
    0.52
    の日
    0.52
    によっては
    0.52
     persons
    0.51
    igot
    0.51
     pellets
    0.51
     visitante
    0.51
    Activations Density 0.127%

    No Known Activations