© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11086
    Prev
    Next
    INDEX
    Explanations

    Iowa and they give

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

    The neuron flags unusually content-rich, informationally salient words—i.e. specific descriptive nouns and adjectives that carry strong topical meaning.

    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
    īgi
    0.68
     szen
    0.57
    ቐ
    0.57
    ād
    0.57
     ば
    0.54
     ৫০০
    0.54
    ació
    0.54
     бай
    0.53
    istical
    0.52
    ಲ್ಯ
    0.52
    POSITIVE LOGITS
    Iowa
    0.88
     Iowa
    0.79
     दुनियाभर
    0.57
    栩
    0.56
     Совет
    0.55
    申込
    0.55
    主席
    0.52
    जत
    0.51
    вав
    0.50
     Ita
    0.50
    Activations Density 0.163%

    No Known Activations