© 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. 6833
    Prev
    Next
    INDEX
    Explanations

    cannot provide advice

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

    This neuron fires on unusually long or low‐frequency “rare” tokens—i.e. the very long, technical or obscure words in the text.

    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
     постави
    0.70
     birçok
    0.69
     tetapi
    0.67
     oameni
    0.67
     ludzi
    0.66
     কয়েকজন
    0.65
     factura
    0.65
    𝓬
    0.65
     también
    0.64
     banyak
    0.64
    POSITIVE LOGITS
     represents
    0.82
     comprises
    0.81
     includes
    0.77
     involves
    0.76
     may
    0.75
     precludes
    0.75
     reflects
    0.74
     relies
    0.74
     consists
    0.73
     cannot
    0.71
    Activations Density 0.027%

    No Known Activations