© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4948
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on occurrences of the preposition “for” (and tokens beginning with “for,” like “front” or “fostering”).

    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
    emiah
    0.89
    ัน
    0.87
    dbox
    0.77
    ையொ
    0.75
    笾
    0.75
    ่อง
    0.75
     Willis
    0.75
     Feldman
    0.75
     міста
    0.74
    蒉
    0.74
    POSITIVE LOGITS
     limpi
    0.84
     rivet
    0.74
     contamin
    0.70
     thrombo
    0.70
     contaminate
    0.69
     permettent
    0.68
     convert
    0.67
     тео
    0.67
     conduire
    0.66
     Motiv
    0.66
    Activations Density 0.022%

    No Known Activations