© 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. 3438
    Prev
    Next
    INDEX
    Explanations

    [mention something specific]

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

    The main thing this neuron does is fire on very high‐frequency/common tokens (especially function words like “and,” “the,” “to,” etc.), essentially marking the most frequent words.

    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
    J
    0.78
    INVALID
    0.76
    зовая
    0.68
    จ
    0.68
    R
    0.68
    JX
    0.67
    ﻨ
    0.66
    ﻌ
    0.66
    亽
    0.66
    ק
    0.65
    POSITIVE LOGITS
     katika
    0.85
     őket
    0.74
     gerektiğini
    0.74
     ketika
    0.73
     amelyek
    0.73
     unei
    0.69
     นี้
    0.68
     onları
    0.68
     kurie
    0.67
     fornire
    0.67
    Activations Density 0.431%

    No Known Activations