© 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. 11511
    Prev
    Next
    INDEX
    Explanations

    especially leading to something

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

    This neuron flags the semantically rich “content” words (uncommon nouns, adjectives, adverbs, and key prepositions) 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
    ។
    0.99
    }.
    0.92
    。《
    0.91
    。
    0.86
    ৷
    0.83
    ։
    0.82
    ም።
    0.82
    .');
    0.81
    ².
    0.80
    .");
    0.80
    POSITIVE LOGITS
     විසින්
    0.73
     Colombeau
    0.69
     Vag
    0.68
     superbly
    0.68
     Clustering
    0.68
     invariably
    0.66
     replete
    0.63
     richly
    0.61
     Ster
    0.61
     توانند
    0.61
    Activations Density 1.438%

    No Known Activations