© 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. 1954
    Prev
    Next
    INDEX
    Explanations

    specifications, areas, threat perceptions

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

    The neuron is specifically triggered by the word “comprehend.”

    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
     paljon
    0.96
     sitten
    0.95
     ∈
    0.88
     maksimum
    0.87
     غوره
    0.86
     ótima
    0.85
     asam
    0.82
     legjobb
    0.82
     толькі
    0.81
     kao
    0.81
    POSITIVE LOGITS
    s
    0.91
    ar
    0.89
    for
    0.81
    un
    0.76
    co
    0.72
    k
    0.68
    ار
    0.66
    h
    0.66
    ق
    0.66
    Y
    0.66
    Activations Density 0.005%

    No Known Activations