© 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. 15041
    Prev
    Next
    INDEX
    Explanations

    analysts and Engineer

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

    The neuron fires strongly on tokens with very high vocabulary indices (i.e. uncommon/rare words in the model’s inventory).

    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
     Concise
    0.75
    nec
    0.75
     concise
    0.74
     revisar
    0.74
    특히
    0.72
    сми
    0.71
     について
    0.71
    ////
    0.70
    嵐
    0.69
    vpc
    0.69
    POSITIVE LOGITS
    ﺑ
    0.80
    学家
    0.77
     absorbed
    0.76
    लिये
    0.75
    WAY
    0.73
    ஜ்மஹ
    0.72
     huống
    0.72
     guessed
    0.71
    来越
    0.70
     flakes
    0.70
    Activations Density 0.000%

    No Known Activations