© 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. 1783
    Prev
    Next
    INDEX
    Explanations

    not intersect

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

    The neuron activates specifically on the term “Apple.”

    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
     “‘
    0.72
    na
    0.71
    j
    0.69
    на
    0.67
    ران
    0.66
    nan
    0.63
    nas
    0.63
    าย
    0.61
    सँग
    0.59
     Delta
    0.58
    POSITIVE LOGITS
    SSL
    0.81
    ωσης
    0.80
    较高的
    0.80
    较大的
    0.79
     vergang
    0.79
    𝗬
    0.79
    鉭
    0.79
     kasih
    0.78
    景象
    0.77
     governador
    0.77
    Activations Density 0.000%

    No Known Activations