© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 7000
    Prev
    Next
    INDEX
    Explanations

    text2IMG conversion

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

    The neuron preferentially flags longer, less common multisyllabic content words (e.g. technical or specialized vocabulary).

    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
    ן
    0.88
    rů
    0.87
    makes
    0.86
    anı
    0.81
    használ
    0.81
    acchati
    0.81
    lés
    0.80
    j
    0.80
    ้
    0.79
    are
    0.78
    POSITIVE LOGITS
     Sebastian
    0.93
     Millennials
    0.83
     Electromagnetic
    0.82
     Metaverse
    0.82
     Crosby
    0.81
     ETFs
    0.81
     Redemption
    0.80
     porte
    0.79
     redemption
    0.79
     emulsion
    0.77
    Activations Density 0.001%

    No Known Activations