© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4703
    Prev
    Next
    INDEX
    Explanations

    can't, still

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

    This neuron strongly fires on common short function words—especially personal pronouns (I, we, you) and auxiliaries/modal verbs—regardless of context.

    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
     أحمد
    1.24
    早速
    1.23
    Baş
    1.18
    ándole
    1.16
    𝗷
    1.16
     Sebelumnya
    1.16
     Chứng
    1.15
    Przyp
    1.12
    今回の
    1.11
    Faz
    1.11
    POSITIVE LOGITS
    .
    1.48
     (
    1.44
     -
    1.38
    /
    1.34
    :
    1.34
     '
    1.23
     /
    1.23
     systems
    1.23
     _
    1.20
    ,
    1.19
    Activations Density 0.664%

    No Known Activations