© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12571
    Prev
    Next
    INDEX
    Explanations

    likely to be

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

    This neuron fires on salient content words—especially longer or more informative nouns, verbs, and adjectives—rather than on common 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
    ренного
    0.53
    اقی
    0.51
     रहेंगे
    0.49
     becomes
    0.49
    ↔
    0.48
     luôn
    0.47
     aina
    0.47
    }{$\
    0.47
    endon
    0.47
     
    0.46
    POSITIVE LOGITS
     probably
    4.34
    probably
    4.19
     Probably
    4.03
    Probably
    4.03
     provavelmente
    4.03
     probablemente
    3.98
     probablement
    3.83
     probabilmente
    3.81
     wahrscheinlich
    3.66
     vermutlich
    3.56
    Activations Density 0.857%

    No Known Activations