© 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. 14088
    Prev
    Next
    INDEX
    Explanations

    cyberpunk, sci-fi, biopunk genres

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

    The neuron is selectively firing on unusually long, multi-syllable words (i.e. very long 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
     estadounidense
    1.02
     estadounidenses
    0.98
     dateFormatter
    0.94
     tamaño
    0.91
    ⃖
    0.89
     желу
    0.89
     यूक
    0.88
     fenómenos
    0.88
     eixo
    0.88
     fárm
    0.87
    POSITIVE LOGITS
    es
    0.80
    v
    0.79
    dle
    0.79
    cid
    0.78
    dor
    0.77
    dling
    0.74
    et
    0.74
    d
    0.73
    ym
    0.73
    cun
    0.73
    Activations Density 0.000%

    No Known Activations