© 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. 11611
    Prev
    Next
    INDEX
    Explanations

    easier to remember or understand

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

    The neuron fires on comparative expressions of ease—most strongly on the word “easier.”

    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
    1
    0.79
     m
    0.74
     M
    0.73
    0.70
     simulated
    0.69
    m
    0.67
     II
    0.66
     product
    0.66
     SE
    0.66
     l
    0.66
    POSITIVE LOGITS
    orrag
    0.82
     énorme
    0.81
    starcore
    0.79
    orgt
    0.79
    addColorStop
    0.78
    <unused2177>
    0.77
    dihydroxy
    0.76
     ആഘോഷ
    0.75
    ckså
    0.73
    childComplexity
    0.71
    Activations Density 0.000%

    No Known Activations