© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2343
    Prev
    Next
    INDEX
    Explanations

    Location, Management, Ideas

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

    The neuron is highly activated by words containing the suffix “ment” (i.e. words ending in “ment”).

    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
    𝒔
    0.89
    کتر
    0.89
    𝘀
    0.82
    𝚜
    0.82
    𝘴
    0.81
    𝑺
    0.81
    𝒑
    0.79
     overwhelmingly
    0.77
     Agenda
    0.77
    𝗽
    0.77
    POSITIVE LOGITS
    Mother
    0.74
    Austria
    0.71
    nés
    0.69
    anje
    0.68
    Marcel
    0.68
     başkan
    0.68
    ාවක්
    0.64
    Turkey
    0.64
    Graphic
    0.63
    RESEARCH
    0.63
    Activations Density 0.002%

    No Known Activations