© 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. 13332
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly at paragraph or section breaks (i.e. the start of a new block of text).

    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
     Related
    0.65
     Поэтому
    0.60
     September
    0.59
     Recently
    0.59
     GSK
    0.59
     June
    0.57
     July
    0.57
    其
    0.57
     Sia
    0.56
     Simultaneously
    0.55
    POSITIVE LOGITS
     semplici
    0.66
     довольно
    0.64
    gameObjects
    0.64
    simpleType
    0.64
     bądź
    0.60
    getType
    0.60
    beginner
    0.60
    ἢ
    0.59
     কিংবা
    0.59
     혹은
    0.58
    Activations Density 4.482%

    No Known Activations