© 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. 14352
    Prev
    Next
    INDEX
    Explanations

    list explanations

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

    This neuron picks out the single “topic” word in each paragraph—the main subject or key noun that best signals what the paragraph is about.

    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
    для
    0.82
    õ
    0.81
    raš
    0.72
     hinsichtlich
    0.72
    ка
    0.71
    ed
    0.70
    rā
    0.70
    vertex
    0.68
    当初
    0.66
    quando
    0.66
    POSITIVE LOGITS
    ួន
    0.94
    ﻋ
    0.84
    𝘐
    0.84
    ﻗ
    0.83
    𝙰
    0.81
    ﺳ
    0.78
     nutrient
    0.77
    ﻟ
    0.77
     botanique
    0.76
    ﯾ
    0.76
    Activations Density 0.000%

    No Known Activations