© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11284
    Prev
    Next
    INDEX
    Explanations

    engage in conversations

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

    The neuron fires on occurrences of the root “engage” (e.g., engage, engaged, engaging, engagement).

    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
     constrain
    0.71
     fieldValue
    0.63
    గం
    0.61
     давление
    0.61
    ниях
    0.59
     inroads
    0.58
     ঢ
    0.57
     fx
    0.57
    லே
    0.57
    ()],
    0.55
    POSITIVE LOGITS
     engaging
    1.27
     engages
    1.26
     engage
    1.24
     engaged
    1.23
    engaged
    1.21
    engage
    1.16
     Engage
    1.15
     engag
    1.13
     engagement
    1.12
    engagement
    1.12
    Activations Density 0.110%

    No Known Activations