© 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. 16071
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to long, formal multi-syllable content words typical of technical or scientific prose (e.g. extracted, information, Circulation).

    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
     vasculaire
    0.85
    ቻል
    0.76
     сотрудников
    0.75
     artistique
    0.75
     soorten
    0.74
    ен
    0.74
    𝚜
    0.73
    olese
    0.73
    वादी
    0.72
    irie
    0.72
    POSITIVE LOGITS
    }]}
    0.73
    Roasted
    0.69
    复制代码
    0.68
    いた
    0.67
    wicz
    0.66
     Disk
    0.66
    斗
    0.66
    )<
    0.66
    WP
    0.64
     pek
    0.64
    Activations Density 0.000%

    No Known Activations