© 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. 5790
    Prev
    Next
    INDEX
    Explanations

    briefly, therapist, pitch, organizations

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

    The neuron fires strongly on words that immediately precede numerical or quantitative values.

    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
    G
    0.88
    Dave
    0.85
    Sku
    0.84
    Steve
    0.81
    都
    0.80
    名
    0.78
    Oi
    0.77
    Agg
    0.76
     Pipe
    0.76
    I
    0.75
    POSITIVE LOGITS
     pierws
    0.82
    nosi
    0.82
     ฝึก
    0.80
     положи
    0.79
     Vallée
    0.79
     fruta
    0.78
     trener
    0.77
     электро
    0.76
     поезд
    0.75
     предприя
    0.75
    Activations Density 0.000%

    No Known Activations