© 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. 14782
    Prev
    Next
    INDEX
    Explanations

    kids exploring, focusing on

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

    The neuron fires strongly on specific named entities and other rare content words (e.g. proper names, unique technical nouns).

    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
    ין
    0.88
    THING
    0.82
    .*?
    0.81
    iu
    0.81
     لين
    0.81
    ผู้ชมในสนาม
    0.79
    ੀ
    0.79
    ième
    0.78
    ieme
    0.77
    TreeNavigator
    0.77
    POSITIVE LOGITS
    add
    0.75
    Кто
    0.71
    älj
    0.69
    9
    0.69
     nombre
    0.68
    خته
    0.66
     années
    0.65
     প্রি
    0.64
    ция
    0.64
    वेळी
    0.64
    Activations Density 0.001%

    No Known Activations