© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6827
    Prev
    Next
    INDEX
    Explanations

    during processes or phases

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

    The neuron fires on explicit date/time markers—especially the word “During” followed by a year or other year‐like number.

    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
     siendo
    0.84
     completing
    0.83
     completed
    0.75
    ار
    0.71
    র
    0.70
     sendo
    0.69
    Being
    0.69
     tendo
    0.69
     décès
    0.69
     ঘণ্টা
    0.68
    POSITIVE LOGITS
     점점
    0.77
     οποίο
    0.71
    最も
    0.70
     transitions
    0.70
     Transitions
    0.68
     Transition
    0.67
     pró
    0.66
    साठी
    0.66
    interfaces
    0.66
    ي
    0.66
    Activations Density 0.101%

    No Known Activations