© 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. 15318
    Prev
    Next
    INDEX
    Explanations

    emboldening and empowering

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

    This neuron responds to rare or unusually infrequent words, flagging tokens that are uncommon or stand out lexically.

    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
    َات
    0.73
    дзі
    0.68
    arters
    0.63
     почи
    0.63
    睇
    0.63
     Ако
    0.62
     ዓይ
    0.61
    emain
    0.61
     ThemeData
    0.61
    ombi
    0.61
    POSITIVE LOGITS
    ’’
    0.82
     criada
    0.82
     mobilier
    0.82
    valores
    0.79
    அல்ல
    0.78
     Corrosion
    0.76
    ﻬ
    0.76
     Vieira
    0.74
    য়াছে
    0.74
     preparada
    0.74
    Activations Density 0.000%

    No Known Activations