© 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. 5241
    Prev
    Next
    INDEX
    Explanations

    effort level (low, medium, high)

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

    This neuron lights up on longer, content-bearing words (especially medium-length nouns) rather than common short function words.

    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
    У
    0.89
    Об
    0.81
    Б
    0.79
    С
    0.76
    Ｃ
    0.74
     ако
    0.73
    Г
    0.70
    Secondo
    0.69
    Пред
    0.69
    Ц
    0.69
    POSITIVE LOGITS
     tights
    1.02
     scarves
    1.02
     halides
    0.99
     unicorns
    0.99
     benefactor
    0.98
     futbol
    0.96
     fútbol
    0.95
     cobbled
    0.95
     porcelain
    0.95
     tacos
    0.92
    Activations Density 0.000%

    No Known Activations