© 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. 12355
    Prev
    Next
    INDEX
    Explanations

    meaning of life

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

    This neuron flags salient content words—key nouns, adjectives, and verbs that carry the main informational load of a sentence.

    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
     বিষয়ের
    0.88
     могла
    0.83
    łącznie
    0.82
     целом
    0.81
    >\<^
    0.81
     digitalisation
    0.79
     えっと
    0.78
     Watercolour
    0.77
     এইরূপে
    0.76
     সাধারণভাবে
    0.76
    POSITIVE LOGITS
     pissed
    1.01
     NFL
    0.98
     NASCAR
    0.92
     nightclubs
    0.89
     Redskins
    0.87
    B
    0.85
     bitch
    0.84
     Pittsburgh
    0.84
     Bakersfield
    0.83
     outlaw
    0.82
    Activations Density 0.108%

    No Known Activations