© 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. 8124
    Prev
    Next
    INDEX
    Explanations

    code block start

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

    This neuron responds to tokens that are uppercase sequences or alphanumeric codes—i.e. acronyms, initialisms, model numbers, and similar technical identifiers.

    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
    که
    0.77
    㐄
    0.68
    </i>
    0.63
    し
    0.63
     ngừa
    0.62
    тельной
    0.62
    ummies
    0.61
     flatter
    0.61
     اعداد
    0.61
    рования
    0.61
    POSITIVE LOGITS
    ί
    0.80
    ن
    0.78
    께
    0.70
     Baillargeon
    0.69
    Newswire
    0.69
     nang
    0.67
    Hoist
    0.67
    يفة
    0.66
    িয়ন
    0.66
    ف
    0.66
    Activations Density 0.014%

    No Known Activations