© 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. 6876
    Prev
    Next
    INDEX
    Explanations

    travel or job specifics

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

    The neuron flags mentions of specific proprietary or trademarked items (e.g. “team,” “characters,” “properties”) in commercial/disclaimer contexts.

    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
     Э
    0.95
    y
    0.95
    l
    0.90
    ル
    0.89
    shire
    0.85
     autonomic
    0.84
    리
    0.82
    마
    0.82
    銨
    0.82
    Mot
    0.80
    POSITIVE LOGITS
    arded
    0.63
    هر
    0.62
     multipliers
    0.59
     Requested
    0.59
     λοι
    0.59
    راف
    0.57
    いても
    0.57
    வடிக்க
    0.57
     وصف
    0.57
    ոչ
    0.57
    Activations Density 0.005%

    No Known Activations