© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11712
    Prev
    Next
    INDEX
    Explanations

    ASOS clothing items

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

    The neuron responds to content‐bearing words—nouns, verbs, and adjectives—rather than to function words.

    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
     میں
    0.70
    的说
    0.66
     är
    0.64
     DDoS
    0.64
    🤯
    0.64
     the
    0.64
     के
    0.64
     में
    0.63
     teie
    0.63
     🔥
    0.61
    POSITIVE LOGITS
     احد
    0.59
    ;\
    0.58
    ;)
    0.56
    ;
    0.56
    翁
    0.56
    ographical
    0.54
    全て
    0.54
     iż
    0.53
    沢山
    0.53
    overall
    0.52
    Activations Density 0.076%

    No Known Activations