© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    Very followed by an adjective describing quality

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

    The main thing this neuron does is detect the adverb “very” used as an intensifier.

    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
    ن
    1.04
    った
    0.94
    мб
    0.89
    িত
    0.89
    न
    0.88
    د
    0.86
    तरी
    0.83
    دول
    0.82
    زاده
    0.80
    끔
    0.79
    POSITIVE LOGITS
    ü
    1.00
    ᅱ
    0.94
    ı
    0.93
    યા
    0.91
    い
    0.91
    ை
    0.90
    ῴ
    0.89
     convoluted
    0.86
    然而
    0.86
    \%
    0.84
    Activations Density 0.062%

    No Known Activations