© 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. 1190
    Prev
    Next
    INDEX
    Explanations

    past actions or attempts

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

    The neuron activates on past‐tense action verbs—especially “I [verb]” statements describing what the speaker did (e.g. “I bought,” “I tried,” “I made”).

    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
     অথবা
    0.62
    NATIONAL
    0.57
     или
    0.55
     หรือ
    0.54
     または
    0.52
    ن
    0.52
     atau
    0.52
     форму
    0.52
     концов
    0.52
    TARIFF
    0.52
    POSITIVE LOGITS
     récemment
    0.70
    샀
    0.70
     recently
    0.65
     ছিলাম
    0.64
     gitti
    0.64
     recentemente
    0.63
     purchased
    0.59
     mangroves
    0.58
     yesterday
    0.57
     glared
    0.56
    Activations Density 0.064%

    No Known Activations