© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5379
    Prev
    Next
    INDEX
    Explanations

    project planning and execution

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

    This neuron spotlights imperative action verbs that introduce job duty or responsibility statements.

    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
    ombok
    0.61
     рублей
    0.58
     треба
    0.58
    ?:
    0.57
    ઃ
    0.54
     ঃ
    0.54
     "":
    0.53
     piede
    0.53
    !:
    0.53
    你在
    0.53
    POSITIVE LOGITS
     including
    0.64
     garner
    0.56
     instit
    0.55
     Advocate
    0.55
     incluyendo
    0.55
    including
    0.55
     รวมถึง
    0.55
    包括
    0.54
     inkl
    0.54
     Odyssey
    0.54
    Activations Density 0.002%

    No Known Activations