© 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. 6803
    Prev
    Next
    INDEX
    Explanations

    young adult

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

    The neuron fires strongly on occurrences of the word “young” (including proper-name uses and references to youth).

    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
     older
    0.79
     elderly
    0.72
     vieille
    0.64
    ítmény
    0.60
     publicados
    0.60
    +)$
    0.59
    older
    0.59
     teammates
    0.59
    ")}}'
    0.58
     quinqu
    0.57
    POSITIVE LOGITS
     Young
    1.00
    Young
    0.82
    blood
    0.78
     젊
    0.71
     Моло
    0.71
     YOUNG
    0.70
     Researchers
    0.67
     mlad
    0.67
    젊
    0.66
    යෙන්
    0.65
    Activations Density 0.074%

    No Known Activations