© 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. 16299
    Prev
    Next
    INDEX
    Explanations

    `"` or other punctuations after "h"

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

    This neuron picks out common short function words—especially prepositions like “to” and “in.”

    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
    devi
    0.82
    e
    0.82
     deviates
    0.77
    د
    0.77
    ل
    0.77
    ai
    0.76
    i
    0.73
    ди
    0.72
     deviate
    0.71
    ই
    0.71
    POSITIVE LOGITS
     Bankr
    0.92
    RGBA
    0.86
    }~\
    0.81
     Juicy
    0.80
     Desai
    0.80
     confertim
    0.80
     setToDefault
    0.78
     Peoria
    0.77
     Grau
    0.77
     方法
    0.77
    Activations Density 0.000%

    No Known Activations