© 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. 5583
    Prev
    Next
    INDEX
    Explanations

    celebrout6meleehighestanyRES

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

    The neuron strongly activates on imperative action verbs that introduce procedural steps (e.g. “boil,” “simmer,” “ping,” “enter”).

    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
    ە
    0.74
    ਿ
    0.67
     M
    0.62
    OOL
    0.61
    棋
    0.61
    дир
    0.60
    ృ
    0.60
     kDa
    0.59
    튬
    0.59
    ool
    0.59
    POSITIVE LOGITS
     निकालकर
    0.81
     necesaria
    0.80
    আধ
    0.77
     típica
    0.77
    цию
    0.76
     gráf
    0.76
    addEnemy
    0.75
    циями
    0.74
    цията
    0.74
     desviación
    0.74
    Activations Density 0.000%

    No Known Activations