© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11594
    Prev
    Next
    INDEX
    Explanations

    the + same/possessive word

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

    The neuron fires strongly on content-bearing keywords (substantive 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_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
     andre
    0.73
     anden
    0.71
    </b>
    0.68
     dette
    0.66
     hospitalized
    0.63
    /";
    0.63
     andra
    0.63
    </h2>
    0.62
     this
    0.62
     данном
    0.61
    POSITIVE LOGITS
     mêmes
    1.04
    রকম
    0.96
     mesmas
    0.95
    一種
    0.93
    一种
    0.93
    ophylline
    0.91
     same
    0.91
    same
    0.91
     mesmos
    0.84
     utmost
    0.83
    Activations Density 0.652%

    No Known Activations