© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11743
    Prev
    Next
    INDEX
    Explanations

    "sweet" milk gives

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

    The neuron selectively responds to Hindi continuous‐aspect verb endings (e.g. the “रहा/रही/रहे … है/हैं/गा/गे” suffixes marking progressive or future‐progressive).

    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_31_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
     является
    0.70
     রয়েছে
    0.70
     রয়েছেন
    0.70
     রয়েছে
    0.68
    에서도
    0.68
     হওয়ার
    0.67
    이다
    0.66
     являются
    0.65
     आहे
    0.64
    에서는
    0.64
    POSITIVE LOGITS
     그걸
    0.69
    と思う
    0.67
    それを
    0.63
     گے
    0.62
    と思って
    0.61
     싶
    0.57
     என்பதை
    0.57
    싶
    0.57
    と思
    0.56
     என்பத
    0.56
    Activations Density 0.011%

    No Known Activations