© 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. 3657
    Prev
    Next
    INDEX
    Explanations

    Un + noun

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

    This neuron detects the substring “un” (in any case) within tokens.

    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
    itudes
    0.91
    에
    0.89
    有时候
    0.82
    两者
    0.82
    {
    0.80
    畯
    0.80
    ances
    0.80
    _
    0.80
    >
    0.79
    }
    0.78
    POSITIVE LOGITS
     autre
    1.34
     montón
    1.30
     altres
    1.20
     cuantos
    1.18
     Vielzahl
    1.14
     sehr
    1.13
     solche
    1.13
     altro
    1.11
     altre
    1.08
     strumento
    1.08
    Activations Density 0.028%

    No Known Activations