© 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. 2495
    Prev
    Next
    INDEX
    Explanations

    setting up or initiating

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

    The neuron detects past-tense verb 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
     полости
    0.63
     чтоб
    0.63
    やお
    0.63
    ние
    0.62
    нию
    0.62
    を楽しむ
    0.62
    ⺀
    0.61
    на
    0.61
    silhouette
    0.60
    ваме
    0.60
    POSITIVE LOGITS
     up
    0.64
    RO
    0.63
    K
    0.58
    HI
    0.57
    RA
    0.57
    ადგენ
    0.56
    Y
    0.54
    AR
    0.53
    AN
    0.53
    LE
    0.53
    Activations Density 0.000%

    No Known Activations