© 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. 24-GEMMASCOPE-2-RES-16K
    7. 13426
    Prev
    Next
    INDEX
    Explanations

    people's actions or states

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

    The neuron strongly activates on occurrences of the word “People.”

    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
     a
    0.98
     অবস্থায়
    0.98
     an
    0.92
     ap
    0.85
    はこちら
    0.85
    有一天
    0.85
     pier
    0.84
     their
    0.83
     undeveloped
    0.83
     the
    0.83
    POSITIVE LOGITS
    ד
    1.34
     publiques
    1.22
    tions
    1.20
    ли
    1.16
    ות
    1.16
    ז
    1.15
    nYou
    1.13
    نا
    1.12
    า
    1.08
    드
    1.05
    Activations Density 0.021%

    No Known Activations