© 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. 1216
    Prev
    Next
    INDEX
    Explanations

    performing actions or operations

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

    This neuron detects procedural or instructional step verbs (e.g. “make,” “carry out,” “perform,” “do,” “go,” “accomplish”) that introduce actions in how-to or procedural descriptions.

    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
     Zombies
    0.81
     coffers
    0.80
    n
    0.79
     participantes
    0.77
     mladi
    0.75
    ę
    0.74
    Password
    0.73
     dedos
    0.73
     capillaries
    0.72
    ̯
    0.72
    POSITIVE LOGITS
    这件事
    0.80
    Согласно
    0.80
    の間
    0.80
    𝗎
    0.79
    此事
    0.78
    ки
    0.77
    ка
    0.76
    𝖽
    0.76
    に基づく
    0.75
    同樣
    0.75
    Activations Density 0.183%

    No Known Activations